diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts
index 6cde070c..2df269d3 100644
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -5,19 +5,87 @@ import type { Model } from "./types.js";
 
 export const MODELS = {
 	"anthropic": {
-		"claude-3-5-haiku-20241022": {
-			id: "claude-3-5-haiku-20241022",
-			name: "Claude Haiku 3.5",
+		"claude-opus-4-0": {
+			id: "claude-opus-4-0",
+			name: "Claude Opus 4 (latest)",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 15,
+				output: 75,
+				cacheRead: 1.5,
+				cacheWrite: 18.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 32000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-3-5-sonnet-20241022": {
+			id: "claude-3-5-sonnet-20241022",
+			name: "Claude Sonnet 3.5 v2",
 			api: "anthropic-messages",
 			provider: "anthropic",
 			baseUrl: "https://api.anthropic.com",
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.8,
-				output: 4,
-				cacheRead: 0.08,
-				cacheWrite: 1,
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 8192,
+		} satisfies Model<"anthropic-messages">,
+		"claude-opus-4-1": {
+			id: "claude-opus-4-1",
+			name: "Claude Opus 4.1 (latest)",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 15,
+				output: 75,
+				cacheRead: 1.5,
+				cacheWrite: 18.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 32000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-haiku-4-5": {
+			id: "claude-haiku-4-5",
+			name: "Claude Haiku 4.5 (latest)",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1,
+				output: 5,
+				cacheRead: 0.1,
+				cacheWrite: 1.25,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-3-5-sonnet-20240620": {
+			id: "claude-3-5-sonnet-20240620",
+			name: "Claude Sonnet 3.5",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
 			},
 			contextWindow: 200000,
 			maxTokens: 8192,
@@ -39,91 +107,23 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
-		"claude-3-5-sonnet-20240620": {
-			id: "claude-3-5-sonnet-20240620",
-			name: "Claude Sonnet 3.5",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 8192,
-		} satisfies Model<"anthropic-messages">,
-		"claude-3-5-sonnet-20241022": {
-			id: "claude-3-5-sonnet-20241022",
-			name: "Claude Sonnet 3.5 v2",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 8192,
-		} satisfies Model<"anthropic-messages">,
-		"claude-3-7-sonnet-20250219": {
-			id: "claude-3-7-sonnet-20250219",
-			name: "Claude Sonnet 3.7",
+		"claude-opus-4-5": {
+			id: "claude-opus-4-5",
+			name: "Claude Opus 4.5 (latest)",
 			api: "anthropic-messages",
 			provider: "anthropic",
 			baseUrl: "https://api.anthropic.com",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
+				input: 5,
+				output: 25,
+				cacheRead: 0.5,
+				cacheWrite: 6.25,
 			},
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
-		"claude-3-7-sonnet-latest": {
-			id: "claude-3-7-sonnet-latest",
-			name: "Claude Sonnet 3.7 (latest)",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"anthropic-messages">,
-		"claude-3-haiku-20240307": {
-			id: "claude-3-haiku-20240307",
-			name: "Claude Haiku 3",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.25,
-				output: 1.25,
-				cacheRead: 0.03,
-				cacheWrite: 0.3,
-			},
-			contextWindow: 200000,
-			maxTokens: 4096,
-		} satisfies Model<"anthropic-messages">,
 		"claude-3-opus-20240229": {
 			id: "claude-3-opus-20240229",
 			name: "Claude Opus 3",
@@ -141,142 +141,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 4096,
 		} satisfies Model<"anthropic-messages">,
-		"claude-3-sonnet-20240229": {
-			id: "claude-3-sonnet-20240229",
-			name: "Claude Sonnet 3",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 0.3,
-			},
-			contextWindow: 200000,
-			maxTokens: 4096,
-		} satisfies Model<"anthropic-messages">,
-		"claude-haiku-4-5": {
-			id: "claude-haiku-4-5",
-			name: "Claude Haiku 4.5 (latest)",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1,
-				output: 5,
-				cacheRead: 0.1,
-				cacheWrite: 1.25,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"anthropic-messages">,
-		"claude-haiku-4-5-20251001": {
-			id: "claude-haiku-4-5-20251001",
-			name: "Claude Haiku 4.5",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1,
-				output: 5,
-				cacheRead: 0.1,
-				cacheWrite: 1.25,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"anthropic-messages">,
-		"claude-opus-4-0": {
-			id: "claude-opus-4-0",
-			name: "Claude Opus 4 (latest)",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 32000,
-		} satisfies Model<"anthropic-messages">,
-		"claude-opus-4-1": {
-			id: "claude-opus-4-1",
-			name: "Claude Opus 4.1 (latest)",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 32000,
-		} satisfies Model<"anthropic-messages">,
-		"claude-opus-4-1-20250805": {
-			id: "claude-opus-4-1-20250805",
-			name: "Claude Opus 4.1",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 32000,
-		} satisfies Model<"anthropic-messages">,
-		"claude-opus-4-20250514": {
-			id: "claude-opus-4-20250514",
-			name: "Claude Opus 4",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 32000,
-		} satisfies Model<"anthropic-messages">,
-		"claude-opus-4-5": {
-			id: "claude-opus-4-5",
-			name: "Claude Opus 4.5 (latest)",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 5,
-				output: 25,
-				cacheRead: 0.5,
-				cacheWrite: 6.25,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"anthropic-messages">,
 		"claude-opus-4-5-20251101": {
 			id: "claude-opus-4-5-20251101",
 			name: "Claude Opus 4.5",
@@ -294,40 +158,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
-		"claude-sonnet-4-0": {
-			id: "claude-sonnet-4-0",
-			name: "Claude Sonnet 4 (latest)",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"anthropic-messages">,
-		"claude-sonnet-4-20250514": {
-			id: "claude-sonnet-4-20250514",
-			name: "Claude Sonnet 4",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"anthropic-messages">,
 		"claude-sonnet-4-5": {
 			id: "claude-sonnet-4-5",
 			name: "Claude Sonnet 4.5 (latest)",
@@ -362,415 +192,467 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
-	},
-	"cerebras": {
-		"gpt-oss-120b": {
-			id: "gpt-oss-120b",
-			name: "GPT OSS 120B",
-			api: "openai-completions",
-			provider: "cerebras",
-			baseUrl: "https://api.cerebras.ai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.25,
-				output: 0.69,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"qwen-3-235b-a22b-instruct-2507": {
-			id: "qwen-3-235b-a22b-instruct-2507",
-			name: "Qwen 3 235B Instruct",
-			api: "openai-completions",
-			provider: "cerebras",
-			baseUrl: "https://api.cerebras.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.6,
-				output: 1.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131000,
-			maxTokens: 32000,
-		} satisfies Model<"openai-completions">,
-		"zai-glm-4.6": {
-			id: "zai-glm-4.6",
-			name: "Z.AI GLM-4.6",
-			api: "openai-completions",
-			provider: "cerebras",
-			baseUrl: "https://api.cerebras.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 40960,
-		} satisfies Model<"openai-completions">,
-	},
-	"github-copilot": {
-		"claude-haiku-4.5": {
-			id: "claude-haiku-4.5",
-			name: "Claude Haiku 4.5",
-			api: "openai-completions",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16000,
-		} satisfies Model<"openai-completions">,
-		"claude-opus-4.5": {
-			id: "claude-opus-4.5",
-			name: "Claude Opus 4.5",
-			api: "openai-completions",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16000,
-		} satisfies Model<"openai-completions">,
-		"claude-sonnet-4": {
-			id: "claude-sonnet-4",
+		"claude-sonnet-4-20250514": {
+			id: "claude-sonnet-4-20250514",
 			name: "Claude Sonnet 4",
-			api: "openai-completions",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16000,
-		} satisfies Model<"openai-completions">,
-		"claude-sonnet-4.5": {
-			id: "claude-sonnet-4.5",
-			name: "Claude Sonnet 4.5",
-			api: "openai-completions",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16000,
-		} satisfies Model<"openai-completions">,
-		"gemini-2.5-pro": {
-			id: "gemini-2.5-pro",
-			name: "Gemini 2.5 Pro",
-			api: "openai-completions",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"gemini-3-flash-preview": {
-			id: "gemini-3-flash-preview",
-			name: "Gemini 3 Flash",
-			api: "openai-completions",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"gemini-3-pro-preview": {
-			id: "gemini-3-pro-preview",
-			name: "Gemini 3 Pro Preview",
-			api: "openai-completions",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"gpt-4.1": {
-			id: "gpt-4.1",
-			name: "GPT-4.1",
-			api: "openai-completions",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"gpt-4o": {
-			id: "gpt-4o",
-			name: "GPT-4o",
-			api: "openai-completions",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 64000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"gpt-5": {
-			id: "gpt-5",
-			name: "GPT-5",
-			api: "openai-responses",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5-codex": {
-			id: "gpt-5-codex",
-			name: "GPT-5-Codex",
-			api: "openai-responses",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5-mini": {
-			id: "gpt-5-mini",
-			name: "GPT-5-mini",
-			api: "openai-responses",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5.1": {
-			id: "gpt-5.1",
-			name: "GPT-5.1",
-			api: "openai-responses",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5.1-codex": {
-			id: "gpt-5.1-codex",
-			name: "GPT-5.1-Codex",
-			api: "openai-responses",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5.1-codex-max": {
-			id: "gpt-5.1-codex-max",
-			name: "GPT-5.1-Codex-max",
-			api: "openai-responses",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5.1-codex-mini": {
-			id: "gpt-5.1-codex-mini",
-			name: "GPT-5.1-Codex-mini",
-			api: "openai-responses",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5.2": {
-			id: "gpt-5.2",
-			name: "GPT-5.2",
-			api: "openai-responses",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-responses">,
-		"grok-code-fast-1": {
-			id: "grok-code-fast-1",
-			name: "Grok Code Fast 1",
-			api: "openai-completions",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"oswe-vscode-prime": {
-			id: "oswe-vscode-prime",
-			name: "Raptor Mini (Preview)",
-			api: "openai-responses",
-			provider: "github-copilot",
-			baseUrl: "https://api.individual.githubcopilot.com",
-			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
 			},
 			contextWindow: 200000,
 			maxTokens: 64000,
-		} satisfies Model<"openai-responses">,
+		} satisfies Model<"anthropic-messages">,
+		"claude-opus-4-20250514": {
+			id: "claude-opus-4-20250514",
+			name: "Claude Opus 4",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 15,
+				output: 75,
+				cacheRead: 1.5,
+				cacheWrite: 18.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 32000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-3-5-haiku-20241022": {
+			id: "claude-3-5-haiku-20241022",
+			name: "Claude Haiku 3.5",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.8,
+				output: 4,
+				cacheRead: 0.08,
+				cacheWrite: 1,
+			},
+			contextWindow: 200000,
+			maxTokens: 8192,
+		} satisfies Model<"anthropic-messages">,
+		"claude-3-haiku-20240307": {
+			id: "claude-3-haiku-20240307",
+			name: "Claude Haiku 3",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 1.25,
+				cacheRead: 0.03,
+				cacheWrite: 0.3,
+			},
+			contextWindow: 200000,
+			maxTokens: 4096,
+		} satisfies Model<"anthropic-messages">,
+		"claude-3-7-sonnet-20250219": {
+			id: "claude-3-7-sonnet-20250219",
+			name: "Claude Sonnet 3.7",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-3-7-sonnet-latest": {
+			id: "claude-3-7-sonnet-latest",
+			name: "Claude Sonnet 3.7 (latest)",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-sonnet-4-0": {
+			id: "claude-sonnet-4-0",
+			name: "Claude Sonnet 4 (latest)",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-opus-4-1-20250805": {
+			id: "claude-opus-4-1-20250805",
+			name: "Claude Opus 4.1",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 15,
+				output: 75,
+				cacheRead: 1.5,
+				cacheWrite: 18.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 32000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-3-sonnet-20240229": {
+			id: "claude-3-sonnet-20240229",
+			name: "Claude Sonnet 3",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 0.3,
+			},
+			contextWindow: 200000,
+			maxTokens: 4096,
+		} satisfies Model<"anthropic-messages">,
+		"claude-haiku-4-5-20251001": {
+			id: "claude-haiku-4-5-20251001",
+			name: "Claude Haiku 4.5",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1,
+				output: 5,
+				cacheRead: 0.1,
+				cacheWrite: 1.25,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"anthropic-messages">,
 	},
 	"google": {
+		"gemini-3-flash-preview": {
+			id: "gemini-3-flash-preview",
+			name: "Gemini 3 Flash Preview",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.5,
+				output: 3,
+				cacheRead: 0.05,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.5-flash-preview-05-20": {
+			id: "gemini-2.5-flash-preview-05-20",
+			name: "Gemini 2.5 Flash Preview 05-20",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.15,
+				output: 0.6,
+				cacheRead: 0.0375,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-flash-lite-latest": {
+			id: "gemini-flash-lite-latest",
+			name: "Gemini Flash-Lite Latest",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.1,
+				output: 0.4,
+				cacheRead: 0.025,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-3-pro-preview": {
+			id: "gemini-3-pro-preview",
+			name: "Gemini 3 Pro Preview",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 12,
+				cacheRead: 0.2,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 64000,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.5-flash": {
+			id: "gemini-2.5-flash",
+			name: "Gemini 2.5 Flash",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.3,
+				output: 2.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-flash-latest": {
+			id: "gemini-flash-latest",
+			name: "Gemini Flash Latest",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.3,
+				output: 2.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.5-pro-preview-05-06": {
+			id: "gemini-2.5-pro-preview-05-06",
+			name: "Gemini 2.5 Pro Preview 05-06",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.31,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.0-flash-lite": {
+			id: "gemini-2.0-flash-lite",
+			name: "Gemini 2.0 Flash Lite",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.075,
+				output: 0.3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 8192,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-live-2.5-flash-preview-native-audio": {
+			id: "gemini-live-2.5-flash-preview-native-audio",
+			name: "Gemini Live 2.5 Flash Preview Native Audio",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.5,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.0-flash": {
+			id: "gemini-2.0-flash",
+			name: "Gemini 2.0 Flash",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.1,
+				output: 0.4,
+				cacheRead: 0.025,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 8192,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.5-flash-lite": {
+			id: "gemini-2.5-flash-lite",
+			name: "Gemini 2.5 Flash Lite",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.1,
+				output: 0.4,
+				cacheRead: 0.025,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.5-pro-preview-06-05": {
+			id: "gemini-2.5-pro-preview-06-05",
+			name: "Gemini 2.5 Pro Preview 06-05",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.31,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-live-2.5-flash": {
+			id: "gemini-live-2.5-flash",
+			name: "Gemini Live 2.5 Flash",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.5,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 8000,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.5-flash-lite-preview-06-17": {
+			id: "gemini-2.5-flash-lite-preview-06-17",
+			name: "Gemini 2.5 Flash Lite Preview 06-17",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.1,
+				output: 0.4,
+				cacheRead: 0.025,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.5-flash-preview-09-2025": {
+			id: "gemini-2.5-flash-preview-09-2025",
+			name: "Gemini 2.5 Flash Preview 09-25",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.3,
+				output: 2.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.5-flash-preview-04-17": {
+			id: "gemini-2.5-flash-preview-04-17",
+			name: "Gemini 2.5 Flash Preview 04-17",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.15,
+				output: 0.6,
+				cacheRead: 0.0375,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.5-pro": {
+			id: "gemini-2.5-pro",
+			name: "Gemini 2.5 Pro",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.31,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
 		"gemini-1.5-flash": {
 			id: "gemini-1.5-flash",
 			name: "Gemini 1.5 Flash",
@@ -805,108 +687,6 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 8192,
 		} satisfies Model<"google-generative-ai">,
-		"gemini-1.5-pro": {
-			id: "gemini-1.5-pro",
-			name: "Gemini 1.5 Pro",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 1.25,
-				output: 5,
-				cacheRead: 0.3125,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 8192,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-2.0-flash": {
-			id: "gemini-2.0-flash",
-			name: "Gemini 2.0 Flash",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.1,
-				output: 0.4,
-				cacheRead: 0.025,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 8192,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-2.0-flash-lite": {
-			id: "gemini-2.0-flash-lite",
-			name: "Gemini 2.0 Flash Lite",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.075,
-				output: 0.3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 8192,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-2.5-flash": {
-			id: "gemini-2.5-flash",
-			name: "Gemini 2.5 Flash",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.3,
-				output: 2.5,
-				cacheRead: 0.075,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-2.5-flash-lite": {
-			id: "gemini-2.5-flash-lite",
-			name: "Gemini 2.5 Flash Lite",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.1,
-				output: 0.4,
-				cacheRead: 0.025,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-2.5-flash-lite-preview-06-17": {
-			id: "gemini-2.5-flash-lite-preview-06-17",
-			name: "Gemini 2.5 Flash Lite Preview 06-17",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.1,
-				output: 0.4,
-				cacheRead: 0.025,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
 		"gemini-2.5-flash-lite-preview-09-2025": {
 			id: "gemini-2.5-flash-lite-preview-09-2025",
 			name: "Gemini 2.5 Flash Lite Preview 09-25",
@@ -924,1120 +704,41 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"google-generative-ai">,
-		"gemini-2.5-flash-preview-04-17": {
-			id: "gemini-2.5-flash-preview-04-17",
-			name: "Gemini 2.5 Flash Preview 04-17",
+		"gemini-1.5-pro": {
+			id: "gemini-1.5-pro",
+			name: "Gemini 1.5 Pro",
 			api: "google-generative-ai",
 			provider: "google",
 			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.15,
-				output: 0.6,
-				cacheRead: 0.0375,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-2.5-flash-preview-05-20": {
-			id: "gemini-2.5-flash-preview-05-20",
-			name: "Gemini 2.5 Flash Preview 05-20",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.15,
-				output: 0.6,
-				cacheRead: 0.0375,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-2.5-flash-preview-09-2025": {
-			id: "gemini-2.5-flash-preview-09-2025",
-			name: "Gemini 2.5 Flash Preview 09-25",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.3,
-				output: 2.5,
-				cacheRead: 0.075,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-2.5-pro": {
-			id: "gemini-2.5-pro",
-			name: "Gemini 2.5 Pro",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
+			reasoning: false,
 			input: ["text", "image"],
 			cost: {
 				input: 1.25,
-				output: 10,
-				cacheRead: 0.31,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-2.5-pro-preview-05-06": {
-			id: "gemini-2.5-pro-preview-05-06",
-			name: "Gemini 2.5 Pro Preview 05-06",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.31,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-2.5-pro-preview-06-05": {
-			id: "gemini-2.5-pro-preview-06-05",
-			name: "Gemini 2.5 Pro Preview 06-05",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.31,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-3-flash-preview": {
-			id: "gemini-3-flash-preview",
-			name: "Gemini 3 Flash Preview",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.5,
-				output: 3,
-				cacheRead: 0.05,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-3-pro-preview": {
-			id: "gemini-3-pro-preview",
-			name: "Gemini 3 Pro Preview",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 12,
-				cacheRead: 0.2,
+				output: 5,
+				cacheRead: 0.3125,
 				cacheWrite: 0,
 			},
 			contextWindow: 1000000,
-			maxTokens: 64000,
+			maxTokens: 8192,
 		} satisfies Model<"google-generative-ai">,
-		"gemini-flash-latest": {
-			id: "gemini-flash-latest",
-			name: "Gemini Flash Latest",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.3,
-				output: 2.5,
-				cacheRead: 0.075,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-flash-lite-latest": {
-			id: "gemini-flash-lite-latest",
-			name: "Gemini Flash-Lite Latest",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
+	},
+	"openai": {
+		"gpt-4.1-nano": {
+			id: "gpt-4.1-nano",
+			name: "GPT-4.1 nano",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
 			input: ["text", "image"],
 			cost: {
 				input: 0.1,
 				output: 0.4,
-				cacheRead: 0.025,
+				cacheRead: 0.03,
 				cacheWrite: 0,
 			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-live-2.5-flash": {
-			id: "gemini-live-2.5-flash",
-			name: "Gemini Live 2.5 Flash",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.5,
-				output: 2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 8000,
-		} satisfies Model<"google-generative-ai">,
-		"gemini-live-2.5-flash-preview-native-audio": {
-			id: "gemini-live-2.5-flash-preview-native-audio",
-			name: "Gemini Live 2.5 Flash Preview Native Audio",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.5,
-				output: 2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 65536,
-		} satisfies Model<"google-generative-ai">,
-	},
-	"google-antigravity": {
-		"claude-opus-4-5-thinking": {
-			id: "claude-opus-4-5-thinking",
-			name: "Claude Opus 4.5 Thinking (Antigravity)",
-			api: "google-gemini-cli",
-			provider: "google-antigravity",
-			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"google-gemini-cli">,
-		"claude-sonnet-4-5": {
-			id: "claude-sonnet-4-5",
-			name: "Claude Sonnet 4.5 (Antigravity)",
-			api: "google-gemini-cli",
-			provider: "google-antigravity",
-			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"google-gemini-cli">,
-		"claude-sonnet-4-5-thinking": {
-			id: "claude-sonnet-4-5-thinking",
-			name: "Claude Sonnet 4.5 Thinking (Antigravity)",
-			api: "google-gemini-cli",
-			provider: "google-antigravity",
-			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"google-gemini-cli">,
-		"gemini-3-flash": {
-			id: "gemini-3-flash",
-			name: "Gemini 3 Flash (Antigravity)",
-			api: "google-gemini-cli",
-			provider: "google-antigravity",
-			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65535,
-		} satisfies Model<"google-gemini-cli">,
-		"gemini-3-pro-high": {
-			id: "gemini-3-pro-high",
-			name: "Gemini 3 Pro High (Antigravity)",
-			api: "google-gemini-cli",
-			provider: "google-antigravity",
-			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65535,
-		} satisfies Model<"google-gemini-cli">,
-		"gemini-3-pro-low": {
-			id: "gemini-3-pro-low",
-			name: "Gemini 3 Pro Low (Antigravity)",
-			api: "google-gemini-cli",
-			provider: "google-antigravity",
-			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65535,
-		} satisfies Model<"google-gemini-cli">,
-		"gpt-oss-120b-medium": {
-			id: "gpt-oss-120b-medium",
-			name: "GPT-OSS 120B Medium (Antigravity)",
-			api: "google-gemini-cli",
-			provider: "google-antigravity",
-			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
+			contextWindow: 1047576,
 			maxTokens: 32768,
-		} satisfies Model<"google-gemini-cli">,
-	},
-	"google-gemini-cli": {
-		"gemini-2.0-flash": {
-			id: "gemini-2.0-flash",
-			name: "Gemini 2.0 Flash (Cloud Code Assist)",
-			api: "google-gemini-cli",
-			provider: "google-gemini-cli",
-			baseUrl: "https://cloudcode-pa.googleapis.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 8192,
-		} satisfies Model<"google-gemini-cli">,
-		"gemini-2.5-flash": {
-			id: "gemini-2.5-flash",
-			name: "Gemini 2.5 Flash (Cloud Code Assist)",
-			api: "google-gemini-cli",
-			provider: "google-gemini-cli",
-			baseUrl: "https://cloudcode-pa.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65535,
-		} satisfies Model<"google-gemini-cli">,
-		"gemini-2.5-pro": {
-			id: "gemini-2.5-pro",
-			name: "Gemini 2.5 Pro (Cloud Code Assist)",
-			api: "google-gemini-cli",
-			provider: "google-gemini-cli",
-			baseUrl: "https://cloudcode-pa.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65535,
-		} satisfies Model<"google-gemini-cli">,
-		"gemini-3-flash-preview": {
-			id: "gemini-3-flash-preview",
-			name: "Gemini 3 Flash Preview (Cloud Code Assist)",
-			api: "google-gemini-cli",
-			provider: "google-gemini-cli",
-			baseUrl: "https://cloudcode-pa.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65535,
-		} satisfies Model<"google-gemini-cli">,
-		"gemini-3-pro-preview": {
-			id: "gemini-3-pro-preview",
-			name: "Gemini 3 Pro Preview (Cloud Code Assist)",
-			api: "google-gemini-cli",
-			provider: "google-gemini-cli",
-			baseUrl: "https://cloudcode-pa.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65535,
-		} satisfies Model<"google-gemini-cli">,
-	},
-	"groq": {
-		"deepseek-r1-distill-llama-70b": {
-			id: "deepseek-r1-distill-llama-70b",
-			name: "DeepSeek R1 Distill Llama 70B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.75,
-				output: 0.99,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"gemma2-9b-it": {
-			id: "gemma2-9b-it",
-			name: "Gemma 2 9B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.2,
-				output: 0.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"llama-3.1-8b-instant": {
-			id: "llama-3.1-8b-instant",
-			name: "Llama 3.1 8B Instant",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.05,
-				output: 0.08,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"llama-3.3-70b-versatile": {
-			id: "llama-3.3-70b-versatile",
-			name: "Llama 3.3 70B Versatile",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.59,
-				output: 0.79,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"llama3-70b-8192": {
-			id: "llama3-70b-8192",
-			name: "Llama 3 70B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.59,
-				output: 0.79,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"llama3-8b-8192": {
-			id: "llama3-8b-8192",
-			name: "Llama 3 8B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.05,
-				output: 0.08,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-4-maverick-17b-128e-instruct": {
-			id: "meta-llama/llama-4-maverick-17b-128e-instruct",
-			name: "Llama 4 Maverick 17B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.2,
-				output: 0.6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-4-scout-17b-16e-instruct": {
-			id: "meta-llama/llama-4-scout-17b-16e-instruct",
-			name: "Llama 4 Scout 17B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.11,
-				output: 0.34,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"mistral-saba-24b": {
-			id: "mistral-saba-24b",
-			name: "Mistral Saba 24B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.79,
-				output: 0.79,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"moonshotai/kimi-k2-instruct": {
-			id: "moonshotai/kimi-k2-instruct",
-			name: "Kimi K2 Instruct",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1,
-				output: 3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"moonshotai/kimi-k2-instruct-0905": {
-			id: "moonshotai/kimi-k2-instruct-0905",
-			name: "Kimi K2 Instruct 0905",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1,
-				output: 3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-oss-120b": {
-			id: "openai/gpt-oss-120b",
-			name: "GPT OSS 120B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.15,
-				output: 0.75,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-oss-20b": {
-			id: "openai/gpt-oss-20b",
-			name: "GPT OSS 20B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.1,
-				output: 0.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"qwen-qwq-32b": {
-			id: "qwen-qwq-32b",
-			name: "Qwen QwQ 32B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.29,
-				output: 0.39,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-32b": {
-			id: "qwen/qwen3-32b",
-			name: "Qwen3 32B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.29,
-				output: 0.59,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-	},
-	"mistral": {
-		"codestral-latest": {
-			id: "codestral-latest",
-			name: "Codestral",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 0.9,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"devstral-2512": {
-			id: "devstral-2512",
-			name: "Devstral 2",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"devstral-medium-2507": {
-			id: "devstral-medium-2507",
-			name: "Devstral Medium",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.4,
-				output: 2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"devstral-medium-latest": {
-			id: "devstral-medium-latest",
-			name: "Devstral 2",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.4,
-				output: 2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"devstral-small-2505": {
-			id: "devstral-small-2505",
-			name: "Devstral Small 2505",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.1,
-				output: 0.3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"devstral-small-2507": {
-			id: "devstral-small-2507",
-			name: "Devstral Small",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.1,
-				output: 0.3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"labs-devstral-small-2512": {
-			id: "labs-devstral-small-2512",
-			name: "Devstral Small 2",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 256000,
-		} satisfies Model<"openai-completions">,
-		"magistral-medium-latest": {
-			id: "magistral-medium-latest",
-			name: "Magistral Medium",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 2,
-				output: 5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"magistral-small": {
-			id: "magistral-small",
-			name: "Magistral Small",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.5,
-				output: 1.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"ministral-3b-latest": {
-			id: "ministral-3b-latest",
-			name: "Ministral 3B",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.04,
-				output: 0.04,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"ministral-8b-latest": {
-			id: "ministral-8b-latest",
-			name: "Ministral 8B",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.1,
-				output: 0.1,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"mistral-large-2411": {
-			id: "mistral-large-2411",
-			name: "Mistral Large 2.1",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 2,
-				output: 6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"mistral-large-2512": {
-			id: "mistral-large-2512",
-			name: "Mistral Large 3",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.5,
-				output: 1.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"mistral-large-latest": {
-			id: "mistral-large-latest",
-			name: "Mistral Large",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.5,
-				output: 1.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"mistral-medium-2505": {
-			id: "mistral-medium-2505",
-			name: "Mistral Medium 3",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.4,
-				output: 2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"mistral-medium-2508": {
-			id: "mistral-medium-2508",
-			name: "Mistral Medium 3.1",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.4,
-				output: 2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"mistral-medium-latest": {
-			id: "mistral-medium-latest",
-			name: "Mistral Medium",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.4,
-				output: 2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"mistral-nemo": {
-			id: "mistral-nemo",
-			name: "Mistral Nemo",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.15,
-				output: 0.15,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"mistral-small-2506": {
-			id: "mistral-small-2506",
-			name: "Mistral Small 3.2",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.1,
-				output: 0.3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"mistral-small-latest": {
-			id: "mistral-small-latest",
-			name: "Mistral Small",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.1,
-				output: 0.3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"open-mistral-7b": {
-			id: "open-mistral-7b",
-			name: "Mistral 7B",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.25,
-				output: 0.25,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8000,
-			maxTokens: 8000,
-		} satisfies Model<"openai-completions">,
-		"open-mixtral-8x22b": {
-			id: "open-mixtral-8x22b",
-			name: "Mixtral 8x22B",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 2,
-				output: 6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 64000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"open-mixtral-8x7b": {
-			id: "open-mixtral-8x7b",
-			name: "Mixtral 8x7B",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.7,
-				output: 0.7,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32000,
-			maxTokens: 32000,
-		} satisfies Model<"openai-completions">,
-		"pixtral-12b": {
-			id: "pixtral-12b",
-			name: "Pixtral 12B",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.15,
-				output: 0.15,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"pixtral-large-latest": {
-			id: "pixtral-large-latest",
-			name: "Pixtral Large",
-			api: "openai-completions",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-	},
-	"openai": {
-		"codex-mini-latest": {
-			id: "codex-mini-latest",
-			name: "Codex Mini",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 1.5,
-				output: 6,
-				cacheRead: 0.375,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
 		} satisfies Model<"openai-responses">,
 		"gpt-4": {
 			id: "gpt-4",
@@ -2056,90 +757,22 @@ export const MODELS = {
 			contextWindow: 8192,
 			maxTokens: 8192,
 		} satisfies Model<"openai-responses">,
-		"gpt-4-turbo": {
-			id: "gpt-4-turbo",
-			name: "GPT-4 Turbo",
+		"o1-pro": {
+			id: "o1-pro",
+			name: "o1-pro",
 			api: "openai-responses",
 			provider: "openai",
 			baseUrl: "https://api.openai.com/v1",
-			reasoning: false,
+			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 10,
-				output: 30,
+				input: 150,
+				output: 600,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-responses">,
-		"gpt-4.1": {
-			id: "gpt-4.1",
-			name: "GPT-4.1",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 8,
-				cacheRead: 0.5,
-				cacheWrite: 0,
-			},
-			contextWindow: 1047576,
-			maxTokens: 32768,
-		} satisfies Model<"openai-responses">,
-		"gpt-4.1-mini": {
-			id: "gpt-4.1-mini",
-			name: "GPT-4.1 mini",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.4,
-				output: 1.6,
-				cacheRead: 0.1,
-				cacheWrite: 0,
-			},
-			contextWindow: 1047576,
-			maxTokens: 32768,
-		} satisfies Model<"openai-responses">,
-		"gpt-4.1-nano": {
-			id: "gpt-4.1-nano",
-			name: "GPT-4.1 nano",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.1,
-				output: 0.4,
-				cacheRead: 0.03,
-				cacheWrite: 0,
-			},
-			contextWindow: 1047576,
-			maxTokens: 32768,
-		} satisfies Model<"openai-responses">,
-		"gpt-4o": {
-			id: "gpt-4o",
-			name: "GPT-4o",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2.5,
-				output: 10,
-				cacheRead: 1.25,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
+			contextWindow: 200000,
+			maxTokens: 100000,
 		} satisfies Model<"openai-responses">,
 		"gpt-4o-2024-05-13": {
 			id: "gpt-4o-2024-05-13",
@@ -2158,6 +791,23 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-responses">,
+		"gpt-5.1-codex": {
+			id: "gpt-5.1-codex",
+			name: "GPT-5.1 Codex",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
 		"gpt-4o-2024-08-06": {
 			id: "gpt-4o-2024-08-06",
 			name: "GPT-4o (2024-08-06)",
@@ -2175,6 +825,295 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 16384,
 		} satisfies Model<"openai-responses">,
+		"gpt-4.1-mini": {
+			id: "gpt-4.1-mini",
+			name: "GPT-4.1 mini",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.4,
+				output: 1.6,
+				cacheRead: 0.1,
+				cacheWrite: 0,
+			},
+			contextWindow: 1047576,
+			maxTokens: 32768,
+		} satisfies Model<"openai-responses">,
+		"o3-deep-research": {
+			id: "o3-deep-research",
+			name: "o3-deep-research",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 10,
+				output: 40,
+				cacheRead: 2.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5.2-pro": {
+			id: "gpt-5.2-pro",
+			name: "GPT-5.2 Pro",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 21,
+				output: 168,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"gpt-4-turbo": {
+			id: "gpt-4-turbo",
+			name: "GPT-4 Turbo",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 10,
+				output: 30,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-responses">,
+		"gpt-5.1-codex-mini": {
+			id: "gpt-5.1-codex-mini",
+			name: "GPT-5.1 Codex mini",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 2,
+				cacheRead: 0.025,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"o3-mini": {
+			id: "o3-mini",
+			name: "o3-mini",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.1,
+				output: 4.4,
+				cacheRead: 0.55,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5.2-chat-latest": {
+			id: "gpt-5.2-chat-latest",
+			name: "GPT-5.2 Chat",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.75,
+				output: 14,
+				cacheRead: 0.175,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-responses">,
+		"gpt-5.1": {
+			id: "gpt-5.1",
+			name: "GPT-5.1",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.13,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"codex-mini-latest": {
+			id: "codex-mini-latest",
+			name: "Codex Mini",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.5,
+				output: 6,
+				cacheRead: 0.375,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5-nano": {
+			id: "gpt-5-nano",
+			name: "GPT-5 Nano",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.05,
+				output: 0.4,
+				cacheRead: 0.01,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5-codex": {
+			id: "gpt-5-codex",
+			name: "GPT-5-Codex",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"gpt-4o": {
+			id: "gpt-4o",
+			name: "GPT-4o",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2.5,
+				output: 10,
+				cacheRead: 1.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-responses">,
+		"gpt-4.1": {
+			id: "gpt-4.1",
+			name: "GPT-4.1",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 8,
+				cacheRead: 0.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 1047576,
+			maxTokens: 32768,
+		} satisfies Model<"openai-responses">,
+		"o4-mini": {
+			id: "o4-mini",
+			name: "o4-mini",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.1,
+				output: 4.4,
+				cacheRead: 0.28,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"o1": {
+			id: "o1",
+			name: "o1",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 15,
+				output: 60,
+				cacheRead: 7.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5-mini": {
+			id: "gpt-5-mini",
+			name: "GPT-5 Mini",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 2,
+				cacheRead: 0.03,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"o3-pro": {
+			id: "o3-pro",
+			name: "o3-pro",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 20,
+				output: 80,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
 		"gpt-4o-2024-11-20": {
 			id: "gpt-4o-2024-11-20",
 			name: "GPT-4o (2024-11-20)",
@@ -2192,6 +1131,57 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 16384,
 		} satisfies Model<"openai-responses">,
+		"gpt-5.1-codex-max": {
+			id: "gpt-5.1-codex-max",
+			name: "GPT-5.1 Codex Max",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"o3": {
+			id: "o3",
+			name: "o3",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 8,
+				cacheRead: 0.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"o4-mini-deep-research": {
+			id: "o4-mini-deep-research",
+			name: "o4-mini-deep-research",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 8,
+				cacheRead: 0.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
 		"gpt-4o-mini": {
 			id: "gpt-4o-mini",
 			name: "GPT-4o mini",
@@ -2226,74 +1216,6 @@ export const MODELS = {
 			contextWindow: 400000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
-		"gpt-5-chat-latest": {
-			id: "gpt-5-chat-latest",
-			name: "GPT-5 Chat Latest",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.125,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-responses">,
-		"gpt-5-codex": {
-			id: "gpt-5-codex",
-			name: "GPT-5-Codex",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.125,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5-mini": {
-			id: "gpt-5-mini",
-			name: "GPT-5 Mini",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.25,
-				output: 2,
-				cacheRead: 0.03,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5-nano": {
-			id: "gpt-5-nano",
-			name: "GPT-5 Nano",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.05,
-				output: 0.4,
-				cacheRead: 0.01,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
 		"gpt-5-pro": {
 			id: "gpt-5-pro",
 			name: "GPT-5 Pro",
@@ -2311,18 +1233,18 @@ export const MODELS = {
 			contextWindow: 400000,
 			maxTokens: 272000,
 		} satisfies Model<"openai-responses">,
-		"gpt-5.1": {
-			id: "gpt-5.1",
-			name: "GPT-5.1",
+		"gpt-5.2": {
+			id: "gpt-5.2",
+			name: "GPT-5.2",
 			api: "openai-responses",
 			provider: "openai",
 			baseUrl: "https://api.openai.com/v1",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.13,
+				input: 1.75,
+				output: 14,
+				cacheRead: 0.175,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -2345,13 +1267,13 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 16384,
 		} satisfies Model<"openai-responses">,
-		"gpt-5.1-codex": {
-			id: "gpt-5.1-codex",
-			name: "GPT-5.1 Codex",
+		"gpt-5-chat-latest": {
+			id: "gpt-5-chat-latest",
+			name: "GPT-5 Chat Latest",
 			api: "openai-responses",
 			provider: "openai",
 			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
+			reasoning: false,
 			input: ["text", "image"],
 			cost: {
 				input: 1.25,
@@ -2359,707 +1281,1615 @@ export const MODELS = {
 				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5.1-codex-max": {
-			id: "gpt-5.1-codex-max",
-			name: "GPT-5.1 Codex Max",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.125,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5.1-codex-mini": {
-			id: "gpt-5.1-codex-mini",
-			name: "GPT-5.1 Codex mini",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.25,
-				output: 2,
-				cacheRead: 0.025,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5.2": {
-			id: "gpt-5.2",
-			name: "GPT-5.2",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.75,
-				output: 14,
-				cacheRead: 0.175,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"gpt-5.2-chat-latest": {
-			id: "gpt-5.2-chat-latest",
-			name: "GPT-5.2 Chat",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.75,
-				output: 14,
-				cacheRead: 0.175,
-				cacheWrite: 0,
-			},
 			contextWindow: 128000,
 			maxTokens: 16384,
 		} satisfies Model<"openai-responses">,
-		"gpt-5.2-pro": {
-			id: "gpt-5.2-pro",
-			name: "GPT-5.2 Pro",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 21,
-				output: 168,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-responses">,
-		"o1": {
-			id: "o1",
-			name: "o1",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 60,
-				cacheRead: 7.5,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
-		"o1-pro": {
-			id: "o1-pro",
-			name: "o1-pro",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 150,
-				output: 600,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
-		"o3": {
-			id: "o3",
-			name: "o3",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 8,
-				cacheRead: 0.5,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
-		"o3-deep-research": {
-			id: "o3-deep-research",
-			name: "o3-deep-research",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 10,
-				output: 40,
-				cacheRead: 2.5,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
-		"o3-mini": {
-			id: "o3-mini",
-			name: "o3-mini",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 1.1,
-				output: 4.4,
-				cacheRead: 0.55,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
-		"o3-pro": {
-			id: "o3-pro",
-			name: "o3-pro",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 20,
-				output: 80,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
-		"o4-mini": {
-			id: "o4-mini",
-			name: "o4-mini",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.1,
-				output: 4.4,
-				cacheRead: 0.28,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
-		"o4-mini-deep-research": {
-			id: "o4-mini-deep-research",
-			name: "o4-mini-deep-research",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 8,
-				cacheRead: 0.5,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
 	},
-	"openrouter": {
-		"ai21/jamba-large-1.7": {
-			id: "ai21/jamba-large-1.7",
-			name: "AI21: Jamba Large 1.7",
+	"groq": {
+		"llama-3.1-8b-instant": {
+			id: "llama-3.1-8b-instant",
+			name: "Llama 3.1 8B Instant",
 			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 2,
-				output: 8,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"ai21/jamba-mini-1.7": {
-			id: "ai21/jamba-mini-1.7",
-			name: "AI21: Jamba Mini 1.7",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.19999999999999998,
-				output: 0.39999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"alibaba/tongyi-deepresearch-30b-a3b": {
-			id: "alibaba/tongyi-deepresearch-30b-a3b",
-			name: "Tongyi DeepResearch 30B A3B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.09,
-				output: 0.39999999999999997,
+				input: 0.05,
+				output: 0.08,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"alibaba/tongyi-deepresearch-30b-a3b:free": {
-			id: "alibaba/tongyi-deepresearch-30b-a3b:free",
-			name: "Tongyi DeepResearch 30B A3B (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"allenai/olmo-3-7b-instruct": {
-			id: "allenai/olmo-3-7b-instruct",
-			name: "AllenAI: Olmo 3 7B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.19999999999999998,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 65536,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"amazon/nova-2-lite-v1": {
-			id: "amazon/nova-2-lite-v1",
-			name: "Amazon: Nova 2 Lite",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.3,
-				output: 2.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 65535,
-		} satisfies Model<"openai-completions">,
-		"amazon/nova-lite-v1": {
-			id: "amazon/nova-lite-v1",
-			name: "Amazon: Nova Lite 1.0",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.06,
-				output: 0.24,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 300000,
-			maxTokens: 5120,
-		} satisfies Model<"openai-completions">,
-		"amazon/nova-micro-v1": {
-			id: "amazon/nova-micro-v1",
-			name: "Amazon: Nova Micro 1.0",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.035,
-				output: 0.14,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 5120,
-		} satisfies Model<"openai-completions">,
-		"amazon/nova-premier-v1": {
-			id: "amazon/nova-premier-v1",
-			name: "Amazon: Nova Premier 1.0",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2.5,
-				output: 12.5,
-				cacheRead: 0.625,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 32000,
-		} satisfies Model<"openai-completions">,
-		"amazon/nova-pro-v1": {
-			id: "amazon/nova-pro-v1",
-			name: "Amazon: Nova Pro 1.0",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.7999999999999999,
-				output: 3.1999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 300000,
-			maxTokens: 5120,
-		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3-haiku": {
-			id: "anthropic/claude-3-haiku",
-			name: "Anthropic: Claude 3 Haiku",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.25,
-				output: 1.25,
-				cacheRead: 0.03,
-				cacheWrite: 0.3,
-			},
-			contextWindow: 200000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3-opus": {
-			id: "anthropic/claude-3-opus",
-			name: "Anthropic: Claude 3 Opus",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3.5-haiku": {
-			id: "anthropic/claude-3.5-haiku",
-			name: "Anthropic: Claude 3.5 Haiku",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.7999999999999999,
-				output: 4,
-				cacheRead: 0.08,
-				cacheWrite: 1,
-			},
-			contextWindow: 200000,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3.5-haiku-20241022": {
-			id: "anthropic/claude-3.5-haiku-20241022",
-			name: "Anthropic: Claude 3.5 Haiku (2024-10-22)",
+		"mistral-saba-24b": {
+			id: "mistral-saba-24b",
+			name: "Mistral Saba 24B",
 			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
 			reasoning: false,
-			input: ["text", "image"],
+			input: ["text"],
 			cost: {
-				input: 0.7999999999999999,
-				output: 4,
-				cacheRead: 0.08,
-				cacheWrite: 1,
-			},
-			contextWindow: 200000,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3.5-sonnet": {
-			id: "anthropic/claude-3.5-sonnet",
-			name: "Anthropic: Claude 3.5 Sonnet",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 6,
-				output: 30,
+				input: 0.79,
+				output: 0.79,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
+			contextWindow: 32768,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"llama3-8b-8192": {
+			id: "llama3-8b-8192",
+			name: "Llama 3 8B",
+			api: "openai-completions",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.05,
+				output: 0.08,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3.7-sonnet": {
-			id: "anthropic/claude-3.7-sonnet",
-			name: "Anthropic: Claude 3.7 Sonnet",
+		"qwen-qwq-32b": {
+			id: "qwen-qwq-32b",
+			name: "Qwen QwQ 32B",
 			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3.7-sonnet:thinking": {
-			id: "anthropic/claude-3.7-sonnet:thinking",
-			name: "Anthropic: Claude 3.7 Sonnet (thinking)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"anthropic/claude-haiku-4.5": {
-			id: "anthropic/claude-haiku-4.5",
-			name: "Anthropic: Claude Haiku 4.5",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1,
-				output: 5,
-				cacheRead: 0.09999999999999999,
-				cacheWrite: 1.25,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"anthropic/claude-opus-4": {
-			id: "anthropic/claude-opus-4",
-			name: "Anthropic: Claude Opus 4",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 32000,
-		} satisfies Model<"openai-completions">,
-		"anthropic/claude-opus-4.1": {
-			id: "anthropic/claude-opus-4.1",
-			name: "Anthropic: Claude Opus 4.1",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"anthropic/claude-opus-4.5": {
-			id: "anthropic/claude-opus-4.5",
-			name: "Anthropic: Claude Opus 4.5",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 5,
-				output: 25,
-				cacheRead: 0.5,
-				cacheWrite: 6.25,
-			},
-			contextWindow: 200000,
-			maxTokens: 32000,
-		} satisfies Model<"openai-completions">,
-		"anthropic/claude-sonnet-4": {
-			id: "anthropic/claude-sonnet-4",
-			name: "Anthropic: Claude Sonnet 4",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 1000000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"anthropic/claude-sonnet-4.5": {
-			id: "anthropic/claude-sonnet-4.5",
-			name: "Anthropic: Claude Sonnet 4.5",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 1000000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"arcee-ai/trinity-mini": {
-			id: "arcee-ai/trinity-mini",
-			name: "Arcee AI: Trinity Mini",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.045,
-				output: 0.15,
+				input: 0.29,
+				output: 0.39,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 131072,
+			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
-		"arcee-ai/trinity-mini:free": {
-			id: "arcee-ai/trinity-mini:free",
-			name: "Arcee AI: Trinity Mini (free)",
+		"llama3-70b-8192": {
+			id: "llama3-70b-8192",
+			name: "Llama 3 70B",
 			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0,
-				output: 0,
+				input: 0.59,
+				output: 0.79,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 4096,
+			contextWindow: 8192,
+			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"arcee-ai/virtuoso-large": {
-			id: "arcee-ai/virtuoso-large",
-			name: "Arcee AI: Virtuoso Large",
+		"deepseek-r1-distill-llama-70b": {
+			id: "deepseek-r1-distill-llama-70b",
+			name: "DeepSeek R1 Distill Llama 70B",
 			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: true,
 			input: ["text"],
 			cost: {
 				input: 0.75,
+				output: 0.99,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"gemma2-9b-it": {
+			id: "gemma2-9b-it",
+			name: "Gemma 2 9B",
+			api: "openai-completions",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.2,
+				output: 0.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"llama-3.3-70b-versatile": {
+			id: "llama-3.3-70b-versatile",
+			name: "Llama 3.3 70B Versatile",
+			api: "openai-completions",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.59,
+				output: 0.79,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"moonshotai/kimi-k2-instruct-0905": {
+			id: "moonshotai/kimi-k2-instruct-0905",
+			name: "Kimi K2 Instruct 0905",
+			api: "openai-completions",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"moonshotai/kimi-k2-instruct": {
+			id: "moonshotai/kimi-k2-instruct",
+			name: "Kimi K2 Instruct",
+			api: "openai-completions",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-oss-20b": {
+			id: "openai/gpt-oss-20b",
+			name: "GPT OSS 20B",
+			api: "openai-completions",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.1,
+				output: 0.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-oss-120b": {
+			id: "openai/gpt-oss-120b",
+			name: "GPT OSS 120B",
+			api: "openai-completions",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.15,
+				output: 0.75,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-32b": {
+			id: "qwen/qwen3-32b",
+			name: "Qwen3 32B",
+			api: "openai-completions",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.29,
+				output: 0.59,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-4-scout-17b-16e-instruct": {
+			id: "meta-llama/llama-4-scout-17b-16e-instruct",
+			name: "Llama 4 Scout 17B",
+			api: "openai-completions",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.11,
+				output: 0.34,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-4-maverick-17b-128e-instruct": {
+			id: "meta-llama/llama-4-maverick-17b-128e-instruct",
+			name: "Llama 4 Maverick 17B",
+			api: "openai-completions",
+			provider: "groq",
+			baseUrl: "https://api.groq.com/openai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.2,
+				output: 0.6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+	},
+	"cerebras": {
+		"qwen-3-235b-a22b-instruct-2507": {
+			id: "qwen-3-235b-a22b-instruct-2507",
+			name: "Qwen 3 235B Instruct",
+			api: "openai-completions",
+			provider: "cerebras",
+			baseUrl: "https://api.cerebras.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.6,
 				output: 1.2,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 64000,
+			contextWindow: 131000,
+			maxTokens: 32000,
 		} satisfies Model<"openai-completions">,
-		"baidu/ernie-4.5-21b-a3b": {
-			id: "baidu/ernie-4.5-21b-a3b",
-			name: "Baidu: ERNIE 4.5 21B A3B",
+		"zai-glm-4.6": {
+			id: "zai-glm-4.6",
+			name: "Z.AI GLM-4.6",
 			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
+			provider: "cerebras",
+			baseUrl: "https://api.cerebras.ai/v1",
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.056,
-				output: 0.224,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 120000,
+			contextWindow: 131072,
+			maxTokens: 40960,
+		} satisfies Model<"openai-completions">,
+		"gpt-oss-120b": {
+			id: "gpt-oss-120b",
+			name: "GPT OSS 120B",
+			api: "openai-completions",
+			provider: "cerebras",
+			baseUrl: "https://api.cerebras.ai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.25,
+				output: 0.69,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+	},
+	"xai": {
+		"grok-4-fast-non-reasoning": {
+			id: "grok-4-fast-non-reasoning",
+			name: "Grok 4 Fast (Non-Reasoning)",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.2,
+				output: 0.5,
+				cacheRead: 0.05,
+				cacheWrite: 0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 30000,
+		} satisfies Model<"openai-completions">,
+		"grok-3-fast": {
+			id: "grok-3-fast",
+			name: "Grok 3 Fast",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 5,
+				output: 25,
+				cacheRead: 1.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"grok-4": {
+			id: "grok-4",
+			name: "Grok 4",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.75,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"grok-2-vision": {
+			id: "grok-2-vision",
+			name: "Grok 2 Vision",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 10,
+				cacheRead: 2,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"grok-code-fast-1": {
+			id: "grok-code-fast-1",
+			name: "Grok Code Fast 1",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.2,
+				output: 1.5,
+				cacheRead: 0.02,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 10000,
+		} satisfies Model<"openai-completions">,
+		"grok-2": {
+			id: "grok-2",
+			name: "Grok 2",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 10,
+				cacheRead: 2,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"grok-3-mini-fast-latest": {
+			id: "grok-3-mini-fast-latest",
+			name: "Grok 3 Mini Fast Latest",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 4,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"grok-2-vision-1212": {
+			id: "grok-2-vision-1212",
+			name: "Grok 2 Vision (1212)",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 10,
+				cacheRead: 2,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"grok-3": {
+			id: "grok-3",
+			name: "Grok 3",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.75,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"grok-4-fast": {
+			id: "grok-4-fast",
+			name: "Grok 4 Fast",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.2,
+				output: 0.5,
+				cacheRead: 0.05,
+				cacheWrite: 0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 30000,
+		} satisfies Model<"openai-completions">,
+		"grok-2-latest": {
+			id: "grok-2-latest",
+			name: "Grok 2 Latest",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 10,
+				cacheRead: 2,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"grok-4-1-fast": {
+			id: "grok-4-1-fast",
+			name: "Grok 4.1 Fast",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.2,
+				output: 0.5,
+				cacheRead: 0.05,
+				cacheWrite: 0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 30000,
+		} satisfies Model<"openai-completions">,
+		"grok-2-1212": {
+			id: "grok-2-1212",
+			name: "Grok 2 (1212)",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 10,
+				cacheRead: 2,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"grok-3-fast-latest": {
+			id: "grok-3-fast-latest",
+			name: "Grok 3 Fast Latest",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 5,
+				output: 25,
+				cacheRead: 1.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"grok-3-latest": {
+			id: "grok-3-latest",
+			name: "Grok 3 Latest",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.75,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"grok-2-vision-latest": {
+			id: "grok-2-vision-latest",
+			name: "Grok 2 Vision Latest",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 10,
+				cacheRead: 2,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"grok-vision-beta": {
+			id: "grok-vision-beta",
+			name: "Grok Vision Beta",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 5,
+				output: 15,
+				cacheRead: 5,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"grok-3-mini": {
+			id: "grok-3-mini",
+			name: "Grok 3 Mini",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 0.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"grok-beta": {
+			id: "grok-beta",
+			name: "Grok Beta",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 5,
+				output: 15,
+				cacheRead: 5,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"grok-3-mini-latest": {
+			id: "grok-3-mini-latest",
+			name: "Grok 3 Mini Latest",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 0.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"grok-4-1-fast-non-reasoning": {
+			id: "grok-4-1-fast-non-reasoning",
+			name: "Grok 4.1 Fast (Non-Reasoning)",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.2,
+				output: 0.5,
+				cacheRead: 0.05,
+				cacheWrite: 0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 30000,
+		} satisfies Model<"openai-completions">,
+		"grok-3-mini-fast": {
+			id: "grok-3-mini-fast",
+			name: "Grok 3 Mini Fast",
+			api: "openai-completions",
+			provider: "xai",
+			baseUrl: "https://api.x.ai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 4,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+	},
+	"zai": {
+		"glm-4.7": {
+			id: "glm-4.7",
+			name: "GLM-4.7",
+			api: "anthropic-messages",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/anthropic",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.2,
+				cacheRead: 0.11,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
+		"glm-4.5-flash": {
+			id: "glm-4.5-flash",
+			name: "GLM-4.5-Flash",
+			api: "anthropic-messages",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/anthropic",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 98304,
+		} satisfies Model<"anthropic-messages">,
+		"glm-4.5": {
+			id: "glm-4.5",
+			name: "GLM-4.5",
+			api: "anthropic-messages",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/anthropic",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.2,
+				cacheRead: 0.11,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 98304,
+		} satisfies Model<"anthropic-messages">,
+		"glm-4.5-air": {
+			id: "glm-4.5-air",
+			name: "GLM-4.5-Air",
+			api: "anthropic-messages",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/anthropic",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.2,
+				output: 1.1,
+				cacheRead: 0.03,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 98304,
+		} satisfies Model<"anthropic-messages">,
+		"glm-4.5v": {
+			id: "glm-4.5v",
+			name: "GLM-4.5V",
+			api: "anthropic-messages",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/anthropic",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.6,
+				output: 1.8,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 64000,
+			maxTokens: 16384,
+		} satisfies Model<"anthropic-messages">,
+		"glm-4.6": {
+			id: "glm-4.6",
+			name: "GLM-4.6",
+			api: "anthropic-messages",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/anthropic",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.2,
+				cacheRead: 0.11,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
+		"glm-4.6v": {
+			id: "glm-4.6v",
+			name: "GLM-4.6V",
+			api: "anthropic-messages",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/anthropic",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.3,
+				output: 0.9,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 32768,
+		} satisfies Model<"anthropic-messages">,
+	},
+	"mistral": {
+		"devstral-medium-2507": {
+			id: "devstral-medium-2507",
+			name: "Devstral Medium",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.4,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"mistral-large-2512": {
+			id: "mistral-large-2512",
+			name: "Mistral Large 3",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.5,
+				output: 1.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"open-mixtral-8x22b": {
+			id: "open-mixtral-8x22b",
+			name: "Mixtral 8x22B",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 64000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"ministral-8b-latest": {
+			id: "ministral-8b-latest",
+			name: "Ministral 8B",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.1,
+				output: 0.1,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"pixtral-large-latest": {
+			id: "pixtral-large-latest",
+			name: "Pixtral Large",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"mistral-small-2506": {
+			id: "mistral-small-2506",
+			name: "Mistral Small 3.2",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.1,
+				output: 0.3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"devstral-2512": {
+			id: "devstral-2512",
+			name: "Devstral 2",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"ministral-3b-latest": {
+			id: "ministral-3b-latest",
+			name: "Ministral 3B",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.04,
+				output: 0.04,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"pixtral-12b": {
+			id: "pixtral-12b",
+			name: "Pixtral 12B",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.15,
+				output: 0.15,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"mistral-medium-2505": {
+			id: "mistral-medium-2505",
+			name: "Mistral Medium 3",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.4,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"labs-devstral-small-2512": {
+			id: "labs-devstral-small-2512",
+			name: "Devstral Small 2",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 256000,
+		} satisfies Model<"openai-completions">,
+		"devstral-medium-latest": {
+			id: "devstral-medium-latest",
+			name: "Devstral 2",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.4,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"devstral-small-2505": {
+			id: "devstral-small-2505",
+			name: "Devstral Small 2505",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.1,
+				output: 0.3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"mistral-medium-2508": {
+			id: "mistral-medium-2508",
+			name: "Mistral Medium 3.1",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.4,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"mistral-small-latest": {
+			id: "mistral-small-latest",
+			name: "Mistral Small",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.1,
+				output: 0.3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"magistral-small": {
+			id: "magistral-small",
+			name: "Magistral Small",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.5,
+				output: 1.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"devstral-small-2507": {
+			id: "devstral-small-2507",
+			name: "Devstral Small",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.1,
+				output: 0.3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"codestral-latest": {
+			id: "codestral-latest",
+			name: "Codestral",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 0.9,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"open-mixtral-8x7b": {
+			id: "open-mixtral-8x7b",
+			name: "Mixtral 8x7B",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.7,
+				output: 0.7,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32000,
+			maxTokens: 32000,
+		} satisfies Model<"openai-completions">,
+		"mistral-nemo": {
+			id: "mistral-nemo",
+			name: "Mistral Nemo",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.15,
+				output: 0.15,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"open-mistral-7b": {
+			id: "open-mistral-7b",
+			name: "Mistral 7B",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.25,
+				output: 0.25,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 8000,
 			maxTokens: 8000,
 		} satisfies Model<"openai-completions">,
-		"baidu/ernie-4.5-vl-28b-a3b": {
-			id: "baidu/ernie-4.5-vl-28b-a3b",
-			name: "Baidu: ERNIE 4.5 VL 28B A3B",
+		"mistral-large-latest": {
+			id: "mistral-large-latest",
+			name: "Mistral Large",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.5,
+				output: 1.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"mistral-medium-latest": {
+			id: "mistral-medium-latest",
+			name: "Mistral Medium",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.4,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"mistral-large-2411": {
+			id: "mistral-large-2411",
+			name: "Mistral Large 2.1",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"magistral-medium-latest": {
+			id: "magistral-medium-latest",
+			name: "Magistral Medium",
+			api: "openai-completions",
+			provider: "mistral",
+			baseUrl: "https://api.mistral.ai/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+	},
+	"github-copilot": {
+		"gemini-3-flash-preview": {
+			id: "gemini-3-flash-preview",
+			name: "Gemini 3 Flash",
+			api: "openai-completions",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"grok-code-fast-1": {
+			id: "grok-code-fast-1",
+			name: "Grok Code Fast 1",
+			api: "openai-completions",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"gpt-5.1-codex": {
+			id: "gpt-5.1-codex",
+			name: "GPT-5.1-Codex",
+			api: "openai-responses",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"claude-haiku-4.5": {
+			id: "claude-haiku-4.5",
+			name: "Claude Haiku 4.5",
+			api: "openai-completions",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16000,
+		} satisfies Model<"openai-completions">,
+		"gemini-3-pro-preview": {
+			id: "gemini-3-pro-preview",
+			name: "Gemini 3 Pro Preview",
+			api: "openai-completions",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"oswe-vscode-prime": {
+			id: "oswe-vscode-prime",
+			name: "Raptor Mini (Preview)",
+			api: "openai-responses",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5.1-codex-mini": {
+			id: "gpt-5.1-codex-mini",
+			name: "GPT-5.1-Codex-mini",
+			api: "openai-responses",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5.1": {
+			id: "gpt-5.1",
+			name: "GPT-5.1",
+			api: "openai-responses",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5-codex": {
+			id: "gpt-5-codex",
+			name: "GPT-5-Codex",
+			api: "openai-responses",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"gpt-4o": {
+			id: "gpt-4o",
+			name: "GPT-4o",
+			api: "openai-completions",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 64000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"gpt-4.1": {
+			id: "gpt-4.1",
+			name: "GPT-4.1",
+			api: "openai-completions",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"gpt-5-mini": {
+			id: "gpt-5-mini",
+			name: "GPT-5-mini",
+			api: "openai-responses",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-responses">,
+		"gemini-2.5-pro": {
+			id: "gemini-2.5-pro",
+			name: "Gemini 2.5 Pro",
+			api: "openai-completions",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"gpt-5.1-codex-max": {
+			id: "gpt-5.1-codex-max",
+			name: "GPT-5.1-Codex-max",
+			api: "openai-responses",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"claude-sonnet-4": {
+			id: "claude-sonnet-4",
+			name: "Claude Sonnet 4",
+			api: "openai-completions",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16000,
+		} satisfies Model<"openai-completions">,
+		"gpt-5": {
+			id: "gpt-5",
+			name: "GPT-5",
+			api: "openai-responses",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"claude-opus-4.5": {
+			id: "claude-opus-4.5",
+			name: "Claude Opus 4.5",
+			api: "openai-completions",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16000,
+		} satisfies Model<"openai-completions">,
+		"gpt-5.2": {
+			id: "gpt-5.2",
+			name: "GPT-5.2",
+			api: "openai-responses",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-responses">,
+		"claude-sonnet-4.5": {
+			id: "claude-sonnet-4.5",
+			name: "Claude Sonnet 4.5",
+			api: "openai-completions",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16000,
+		} satisfies Model<"openai-completions">,
+	},
+	"openrouter": {
+		"bytedance-seed/seed-1.6-flash": {
+			id: "bytedance-seed/seed-1.6-flash",
+			name: "ByteDance Seed: Seed 1.6 Flash",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.112,
-				output: 0.448,
+				input: 0.075,
+				output: 0.3,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 30000,
-			maxTokens: 8000,
+			contextWindow: 262144,
+			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"bytedance-seed/seed-1.6": {
 			id: "bytedance-seed/seed-1.6",
@@ -3078,162 +2908,9 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
-		"bytedance-seed/seed-1.6-flash": {
-			id: "bytedance-seed/seed-1.6-flash",
-			name: "ByteDance Seed: Seed 1.6 Flash",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.075,
-				output: 0.3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"cohere/command-r-08-2024": {
-			id: "cohere/command-r-08-2024",
-			name: "Cohere: Command R (08-2024)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.15,
-				output: 0.6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4000,
-		} satisfies Model<"openai-completions">,
-		"cohere/command-r-plus-08-2024": {
-			id: "cohere/command-r-plus-08-2024",
-			name: "Cohere: Command R+ (08-2024)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 2.5,
-				output: 10,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4000,
-		} satisfies Model<"openai-completions">,
-		"deepcogito/cogito-v2-preview-llama-109b-moe": {
-			id: "deepcogito/cogito-v2-preview-llama-109b-moe",
-			name: "Cogito V2 Preview Llama 109B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.18,
-				output: 0.59,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32767,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"deepcogito/cogito-v2-preview-llama-405b": {
-			id: "deepcogito/cogito-v2-preview-llama-405b",
-			name: "Deep Cogito: Cogito V2 Preview Llama 405B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 3.5,
-				output: 3.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"deepcogito/cogito-v2-preview-llama-70b": {
-			id: "deepcogito/cogito-v2-preview-llama-70b",
-			name: "Deep Cogito: Cogito V2 Preview Llama 70B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.88,
-				output: 0.88,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"deepseek/deepseek-chat": {
-			id: "deepseek/deepseek-chat",
-			name: "DeepSeek: DeepSeek V3",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 1.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 163840,
-		} satisfies Model<"openai-completions">,
-		"deepseek/deepseek-chat-v3-0324": {
-			id: "deepseek/deepseek-chat-v3-0324",
-			name: "DeepSeek: DeepSeek V3 0324",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.19999999999999998,
-				output: 0.88,
-				cacheRead: 0.106,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"deepseek/deepseek-chat-v3.1": {
-			id: "deepseek/deepseek-chat-v3.1",
-			name: "DeepSeek: DeepSeek V3.1",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.15,
-				output: 0.75,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 7168,
-		} satisfies Model<"openai-completions">,
-		"deepseek/deepseek-r1": {
-			id: "deepseek/deepseek-r1",
-			name: "DeepSeek: R1",
+		"minimax/minimax-m2.1": {
+			id: "minimax/minimax-m2.1",
+			name: "MiniMax: MiniMax M2.1",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
@@ -3242,15 +2919,15 @@ export const MODELS = {
 			cost: {
 				input: 0.3,
 				output: 1.2,
-				cacheRead: 0,
-				cacheWrite: 0,
+				cacheRead: 0.03,
+				cacheWrite: 0.375,
 			},
-			contextWindow: 163840,
-			maxTokens: 4096,
+			contextWindow: 204800,
+			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
-		"deepseek/deepseek-r1-0528": {
-			id: "deepseek/deepseek-r1-0528",
-			name: "DeepSeek: R1 0528",
+		"z-ai/glm-4.7": {
+			id: "z-ai/glm-4.7",
+			name: "Z.AI: GLM 4.7",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
@@ -3258,266 +2935,11 @@ export const MODELS = {
 			input: ["text"],
 			cost: {
 				input: 0.39999999999999997,
-				output: 1.75,
+				output: 1.5,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 163840,
-			maxTokens: 163840,
-		} satisfies Model<"openai-completions">,
-		"deepseek/deepseek-r1-distill-llama-70b": {
-			id: "deepseek/deepseek-r1-distill-llama-70b",
-			name: "DeepSeek: R1 Distill Llama 70B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.03,
-				output: 0.11,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"deepseek/deepseek-v3.1-terminus": {
-			id: "deepseek/deepseek-v3.1-terminus",
-			name: "DeepSeek: DeepSeek V3.1 Terminus",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.21,
-				output: 0.7899999999999999,
-				cacheRead: 0.16799999999999998,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"deepseek/deepseek-v3.1-terminus:exacto": {
-			id: "deepseek/deepseek-v3.1-terminus:exacto",
-			name: "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.21,
-				output: 0.7899999999999999,
-				cacheRead: 0.16799999999999998,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"deepseek/deepseek-v3.2": {
-			id: "deepseek/deepseek-v3.2",
-			name: "DeepSeek: DeepSeek V3.2",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.224,
-				output: 0.32,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"deepseek/deepseek-v3.2-exp": {
-			id: "deepseek/deepseek-v3.2-exp",
-			name: "DeepSeek: DeepSeek V3.2 Exp",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.21,
-				output: 0.32,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"google/gemini-2.0-flash-001": {
-			id: "google/gemini-2.0-flash-001",
-			name: "Google: Gemini 2.0 Flash",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.39999999999999997,
-				cacheRead: 0.024999999999999998,
-				cacheWrite: 0.18330000000000002,
-			},
-			contextWindow: 1048576,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"google/gemini-2.0-flash-exp:free": {
-			id: "google/gemini-2.0-flash-exp:free",
-			name: "Google: Gemini 2.0 Flash Experimental (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"google/gemini-2.0-flash-lite-001": {
-			id: "google/gemini-2.0-flash-lite-001",
-			name: "Google: Gemini 2.0 Flash Lite",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.075,
-				output: 0.3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"google/gemini-2.5-flash": {
-			id: "google/gemini-2.5-flash",
-			name: "Google: Gemini 2.5 Flash",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.3,
-				output: 2.5,
-				cacheRead: 0.03,
-				cacheWrite: 0.3833,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65535,
-		} satisfies Model<"openai-completions">,
-		"google/gemini-2.5-flash-lite": {
-			id: "google/gemini-2.5-flash-lite",
-			name: "Google: Gemini 2.5 Flash Lite",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.39999999999999997,
-				cacheRead: 0.01,
-				cacheWrite: 0.18330000000000002,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65535,
-		} satisfies Model<"openai-completions">,
-		"google/gemini-2.5-flash-lite-preview-09-2025": {
-			id: "google/gemini-2.5-flash-lite-preview-09-2025",
-			name: "Google: Gemini 2.5 Flash Lite Preview 09-2025",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.39999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"google/gemini-2.5-flash-preview-09-2025": {
-			id: "google/gemini-2.5-flash-preview-09-2025",
-			name: "Google: Gemini 2.5 Flash Preview 09-2025",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.3,
-				output: 2.5,
-				cacheRead: 0.075,
-				cacheWrite: 0.3833,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"google/gemini-2.5-pro": {
-			id: "google/gemini-2.5-pro",
-			name: "Google: Gemini 2.5 Pro",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.125,
-				cacheWrite: 1.625,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"google/gemini-2.5-pro-preview": {
-			id: "google/gemini-2.5-pro-preview",
-			name: "Google: Gemini 2.5 Pro Preview 06-05",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.31,
-				cacheWrite: 1.625,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"google/gemini-2.5-pro-preview-05-06": {
-			id: "google/gemini-2.5-pro-preview-05-06",
-			name: "Google: Gemini 2.5 Pro Preview 05-06",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.31,
-				cacheWrite: 1.625,
-			},
-			contextWindow: 1048576,
+			contextWindow: 202752,
 			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
 		"google/gemini-3-flash-preview": {
@@ -3537,213 +2959,9 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
-		"google/gemini-3-pro-preview": {
-			id: "google/gemini-3-pro-preview",
-			name: "Google: Gemini 3 Pro Preview",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 12,
-				cacheRead: 0.19999999999999998,
-				cacheWrite: 2.375,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"google/gemma-3-27b-it": {
-			id: "google/gemma-3-27b-it",
-			name: "Google: Gemma 3 27B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.04,
-				output: 0.15,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 96000,
-			maxTokens: 96000,
-		} satisfies Model<"openai-completions">,
-		"google/gemma-3-27b-it:free": {
-			id: "google/gemma-3-27b-it:free",
-			name: "Google: Gemma 3 27B (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"inception/mercury": {
-			id: "inception/mercury",
-			name: "Inception: Mercury",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.25,
-				output: 1,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"inception/mercury-coder": {
-			id: "inception/mercury-coder",
-			name: "Inception: Mercury Coder",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.25,
-				output: 1,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"kwaipilot/kat-coder-pro:free": {
-			id: "kwaipilot/kat-coder-pro:free",
-			name: "Kwaipilot: KAT-Coder-Pro V1 (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3-70b-instruct": {
-			id: "meta-llama/llama-3-70b-instruct",
-			name: "Meta: Llama 3 70B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 0.39999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3-8b-instruct": {
-			id: "meta-llama/llama-3-8b-instruct",
-			name: "Meta: Llama 3 8B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.03,
-				output: 0.06,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3.1-405b-instruct": {
-			id: "meta-llama/llama-3.1-405b-instruct",
-			name: "Meta: Llama 3.1 405B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 3.5,
-				output: 3.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 10000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3.1-70b-instruct": {
-			id: "meta-llama/llama-3.1-70b-instruct",
-			name: "Meta: Llama 3.1 70B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.39999999999999997,
-				output: 0.39999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3.1-8b-instruct": {
-			id: "meta-llama/llama-3.1-8b-instruct",
-			name: "Meta: Llama 3.1 8B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.02,
-				output: 0.03,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3.2-3b-instruct": {
-			id: "meta-llama/llama-3.2-3b-instruct",
-			name: "Meta: Llama 3.2 3B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.02,
-				output: 0.02,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3.3-70b-instruct": {
-			id: "meta-llama/llama-3.3-70b-instruct",
-			name: "Meta: Llama 3.3 70B Instruct",
+		"mistralai/mistral-small-creative": {
+			id: "mistralai/mistral-small-creative",
+			name: "Mistral: Mistral Small Creative",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
@@ -3751,183 +2969,132 @@ export const MODELS = {
 			input: ["text"],
 			cost: {
 				input: 0.09999999999999999,
-				output: 0.32,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-3.3-70b-instruct:free": {
-			id: "meta-llama/llama-3.3-70b-instruct:free",
-			name: "Meta: Llama 3.3 70B Instruct (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-4-maverick": {
-			id: "meta-llama/llama-4-maverick",
-			name: "Meta: Llama 4 Maverick",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.15,
-				output: 0.6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"meta-llama/llama-4-scout": {
-			id: "meta-llama/llama-4-scout",
-			name: "Meta: Llama 4 Scout",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.08,
 				output: 0.3,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 327680,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"microsoft/phi-3-medium-128k-instruct": {
-			id: "microsoft/phi-3-medium-128k-instruct",
-			name: "Microsoft: Phi-3 Medium 128K Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1,
-				output: 1,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
+			contextWindow: 32768,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"microsoft/phi-3-mini-128k-instruct": {
-			id: "microsoft/phi-3-mini-128k-instruct",
-			name: "Microsoft: Phi-3 Mini 128K Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"microsoft/phi-3.5-mini-128k-instruct": {
-			id: "microsoft/phi-3.5-mini-128k-instruct",
-			name: "Microsoft: Phi-3.5 Mini 128K Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"minimax/minimax-m1": {
-			id: "minimax/minimax-m1",
-			name: "MiniMax: MiniMax M1",
+		"xiaomi/mimo-v2-flash:free": {
+			id: "xiaomi/mimo-v2-flash:free",
+			name: "Xiaomi: MiMo-V2-Flash (free)",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.39999999999999997,
-				output: 2.2,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 1000000,
-			maxTokens: 40000,
+			contextWindow: 262144,
+			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"minimax/minimax-m2": {
-			id: "minimax/minimax-m2",
-			name: "MiniMax: MiniMax M2",
+		"nvidia/nemotron-3-nano-30b-a3b:free": {
+			id: "nvidia/nemotron-3-nano-30b-a3b:free",
+			name: "NVIDIA: Nemotron 3 Nano 30B A3B (free)",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.19999999999999998,
-				output: 1,
-				cacheRead: 0.03,
-				cacheWrite: 0,
-			},
-			contextWindow: 196608,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"minimax/minimax-m2.1": {
-			id: "minimax/minimax-m2.1",
-			name: "MiniMax: MiniMax M2.1",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 1.2,
-				cacheRead: 0.03,
-				cacheWrite: 0.375,
-			},
-			contextWindow: 204800,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"mistralai/codestral-2508": {
-			id: "mistralai/codestral-2508",
-			name: "Mistral: Codestral 2508",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 0.8999999999999999,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"nvidia/nemotron-3-nano-30b-a3b": {
+			id: "nvidia/nemotron-3-nano-30b-a3b",
+			name: "NVIDIA: Nemotron 3 Nano 30B A3B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.06,
+				output: 0.24,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-5.2-chat": {
+			id: "openai/gpt-5.2-chat",
+			name: "OpenAI: GPT-5.2 Chat",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 1.75,
+				output: 14,
+				cacheRead: 0.175,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-5.2-pro": {
+			id: "openai/gpt-5.2-pro",
+			name: "OpenAI: GPT-5.2 Pro",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 21,
+				output: 168,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-5.2": {
+			id: "openai/gpt-5.2",
+			name: "OpenAI: GPT-5.2",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.75,
+				output: 14,
+				cacheRead: 0.175,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"mistralai/devstral-2512:free": {
+			id: "mistralai/devstral-2512:free",
+			name: "Mistral: Devstral 2 2512 (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"mistralai/devstral-2512": {
 			id: "mistralai/devstral-2512",
 			name: "Mistral: Devstral 2 2512",
@@ -3945,9 +3112,43 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"mistralai/devstral-2512:free": {
-			id: "mistralai/devstral-2512:free",
-			name: "Mistral: Devstral 2 2512 (free)",
+		"relace/relace-search": {
+			id: "relace/relace-search",
+			name: "Relace: Relace Search",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"z-ai/glm-4.6v": {
+			id: "z-ai/glm-4.6v",
+			name: "Z.AI: GLM 4.6V",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.3,
+				output: 0.8999999999999999,
+				cacheRead: 0.049999999999999996,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 24000,
+		} satisfies Model<"openai-completions">,
+		"nex-agi/deepseek-v3.1-nex-n1:free": {
+			id: "nex-agi/deepseek-v3.1-nex-n1:free",
+			name: "Nex AGI: DeepSeek V3.1 Nex N1 (free)",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
@@ -3959,42 +3160,42 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 262144,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/devstral-medium": {
-			id: "mistralai/devstral-medium",
-			name: "Mistral: Devstral Medium",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.39999999999999997,
-				output: 2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
 			contextWindow: 131072,
-			maxTokens: 4096,
+			maxTokens: 163840,
 		} satisfies Model<"openai-completions">,
-		"mistralai/devstral-small": {
-			id: "mistralai/devstral-small",
-			name: "Mistral: Devstral Small 1.1",
+		"openai/gpt-5.1-codex-max": {
+			id: "openai/gpt-5.1-codex-max",
+			name: "OpenAI: GPT-5.1-Codex-Max",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
+			reasoning: true,
+			input: ["text", "image"],
 			cost: {
-				input: 0.07,
-				output: 0.28,
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"amazon/nova-2-lite-v1": {
+			id: "amazon/nova-2-lite-v1",
+			name: "Amazon: Nova 2 Lite",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.3,
+				output: 2.5,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
-			maxTokens: 4096,
+			contextWindow: 1000000,
+			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
 		"mistralai/ministral-14b-2512": {
 			id: "mistralai/ministral-14b-2512",
@@ -4013,57 +3214,6 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"mistralai/ministral-3b": {
-			id: "mistralai/ministral-3b",
-			name: "Mistral: Ministral 3B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.04,
-				output: 0.04,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/ministral-3b-2512": {
-			id: "mistralai/ministral-3b-2512",
-			name: "Mistral: Ministral 3 3B 2512",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/ministral-8b": {
-			id: "mistralai/ministral-8b",
-			name: "Mistral: Ministral 8B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"mistralai/ministral-8b-2512": {
 			id: "mistralai/ministral-8b-2512",
 			name: "Mistral: Ministral 3 8B 2512",
@@ -4081,85 +3231,17 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-7b-instruct": {
-			id: "mistralai/mistral-7b-instruct",
-			name: "Mistral: Mistral 7B Instruct",
+		"mistralai/ministral-3b-2512": {
+			id: "mistralai/ministral-3b-2512",
+			name: "Mistral: Ministral 3 3B 2512",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: false,
-			input: ["text"],
+			input: ["text", "image"],
 			cost: {
-				input: 0.028,
-				output: 0.054,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-7b-instruct:free": {
-			id: "mistralai/mistral-7b-instruct:free",
-			name: "Mistral: Mistral 7B Instruct (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-large": {
-			id: "mistralai/mistral-large",
-			name: "Mistral Large",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 2,
-				output: 6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-large-2407": {
-			id: "mistralai/mistral-large-2407",
-			name: "Mistral Large 2407",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 2,
-				output: 6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-large-2411": {
-			id: "mistralai/mistral-large-2411",
-			name: "Mistral Large 2411",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 2,
-				output: 6,
+				input: 0.09999999999999999,
+				output: 0.09999999999999999,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -4183,366 +3265,94 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-medium-3": {
-			id: "mistralai/mistral-medium-3",
-			name: "Mistral: Mistral Medium 3",
+		"arcee-ai/trinity-mini:free": {
+			id: "arcee-ai/trinity-mini:free",
+			name: "Arcee AI: Trinity Mini (free)",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.39999999999999997,
-				output: 2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-medium-3.1": {
-			id: "mistralai/mistral-medium-3.1",
-			name: "Mistral: Mistral Medium 3.1",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.39999999999999997,
-				output: 2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-nemo": {
-			id: "mistralai/mistral-nemo",
-			name: "Mistral: Mistral Nemo",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
+			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.02,
-				output: 0.04,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 16384,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-saba": {
-			id: "mistralai/mistral-saba",
-			name: "Mistral: Saba",
+		"arcee-ai/trinity-mini": {
+			id: "arcee-ai/trinity-mini",
+			name: "Arcee AI: Trinity Mini",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.045,
+				output: 0.15,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"deepseek/deepseek-v3.2": {
+			id: "deepseek/deepseek-v3.2",
+			name: "DeepSeek: DeepSeek V3.2",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.224,
+				output: 0.32,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 163840,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"prime-intellect/intellect-3": {
+			id: "prime-intellect/intellect-3",
+			name: "Prime Intellect: INTELLECT-3",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
 			input: ["text"],
 			cost: {
 				input: 0.19999999999999998,
-				output: 0.6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-small-24b-instruct-2501": {
-			id: "mistralai/mistral-small-24b-instruct-2501",
-			name: "Mistral: Mistral Small 3",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.03,
-				output: 0.11,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-small-3.1-24b-instruct": {
-			id: "mistralai/mistral-small-3.1-24b-instruct",
-			name: "Mistral: Mistral Small 3.1 24B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.03,
-				output: 0.11,
+				output: 1.1,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-small-3.1-24b-instruct:free": {
-			id: "mistralai/mistral-small-3.1-24b-instruct:free",
-			name: "Mistral: Mistral Small 3.1 24B (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-small-3.2-24b-instruct": {
-			id: "mistralai/mistral-small-3.2-24b-instruct",
-			name: "Mistral: Mistral Small 3.2 24B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.06,
-				output: 0.18,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-small-creative": {
-			id: "mistralai/mistral-small-creative",
-			name: "Mistral: Mistral Small Creative",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-tiny": {
-			id: "mistralai/mistral-tiny",
-			name: "Mistral Tiny",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.25,
-				output: 0.25,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mixtral-8x22b-instruct": {
-			id: "mistralai/mixtral-8x22b-instruct",
-			name: "Mistral: Mixtral 8x22B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 2,
-				output: 6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 65536,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/mixtral-8x7b-instruct": {
-			id: "mistralai/mixtral-8x7b-instruct",
-			name: "Mistral: Mixtral 8x7B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.54,
-				output: 0.54,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"mistralai/pixtral-12b": {
-			id: "mistralai/pixtral-12b",
-			name: "Mistral: Pixtral 12B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/pixtral-large-2411": {
-			id: "mistralai/pixtral-large-2411",
-			name: "Mistral: Pixtral Large 2411",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"mistralai/voxtral-small-24b-2507": {
-			id: "mistralai/voxtral-small-24b-2507",
-			name: "Mistral: Voxtral Small 24B 2507",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"moonshotai/kimi-k2": {
-			id: "moonshotai/kimi-k2",
-			name: "MoonshotAI: Kimi K2 0711",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.456,
-				output: 1.8399999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"moonshotai/kimi-k2-0905": {
-			id: "moonshotai/kimi-k2-0905",
-			name: "MoonshotAI: Kimi K2 0905",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.39,
-				output: 1.9,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"moonshotai/kimi-k2-0905:exacto": {
-			id: "moonshotai/kimi-k2-0905:exacto",
-			name: "MoonshotAI: Kimi K2 0905 (exacto)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.6,
-				output: 2.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"moonshotai/kimi-k2-thinking": {
-			id: "moonshotai/kimi-k2-thinking",
-			name: "MoonshotAI: Kimi K2 Thinking",
+		"tngtech/tng-r1t-chimera:free": {
+			id: "tngtech/tng-r1t-chimera:free",
+			name: "TNG: R1T Chimera (free)",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text"],
-			cost: {
-				input: 0.39999999999999997,
-				output: 1.75,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 65535,
-		} satisfies Model<"openai-completions">,
-		"nex-agi/deepseek-v3.1-nex-n1:free": {
-			id: "nex-agi/deepseek-v3.1-nex-n1:free",
-			name: "Nex AGI: DeepSeek V3.1 Nex N1 (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
 			cost: {
 				input: 0,
 				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
+			contextWindow: 163840,
 			maxTokens: 163840,
 		} satisfies Model<"openai-completions">,
-		"nousresearch/deephermes-3-mistral-24b-preview": {
-			id: "nousresearch/deephermes-3-mistral-24b-preview",
-			name: "Nous: DeepHermes 3 Mistral 24B Preview",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.02,
-				output: 0.09999999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"nousresearch/hermes-4-405b": {
-			id: "nousresearch/hermes-4-405b",
-			name: "Nous: Hermes 4 405B",
+		"tngtech/tng-r1t-chimera": {
+			id: "tngtech/tng-r1t-chimera",
+			name: "TNG: R1T Chimera",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
@@ -4554,603 +3364,76 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 131072,
+			contextWindow: 163840,
+			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"nousresearch/hermes-4-70b": {
-			id: "nousresearch/hermes-4-70b",
-			name: "Nous: Hermes 4 70B",
+		"anthropic/claude-opus-4.5": {
+			id: "anthropic/claude-opus-4.5",
+			name: "Anthropic: Claude Opus 4.5",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.11,
-				output: 0.38,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"nvidia/llama-3.1-nemotron-70b-instruct": {
-			id: "nvidia/llama-3.1-nemotron-70b-instruct",
-			name: "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1.2,
-				output: 1.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
-			id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
-			name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.39999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"nvidia/nemotron-3-nano-30b-a3b": {
-			id: "nvidia/nemotron-3-nano-30b-a3b",
-			name: "NVIDIA: Nemotron 3 Nano 30B A3B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.06,
-				output: 0.24,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"nvidia/nemotron-3-nano-30b-a3b:free": {
-			id: "nvidia/nemotron-3-nano-30b-a3b:free",
-			name: "NVIDIA: Nemotron 3 Nano 30B A3B (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"nvidia/nemotron-nano-12b-v2-vl:free": {
-			id: "nvidia/nemotron-nano-12b-v2-vl:free",
-			name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"nvidia/nemotron-nano-9b-v2": {
-			id: "nvidia/nemotron-nano-9b-v2",
-			name: "NVIDIA: Nemotron Nano 9B V2",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.04,
-				output: 0.16,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"nvidia/nemotron-nano-9b-v2:free": {
-			id: "nvidia/nemotron-nano-9b-v2:free",
-			name: "NVIDIA: Nemotron Nano 9B V2 (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/codex-mini": {
-			id: "openai/codex-mini",
-			name: "OpenAI: Codex Mini",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.5,
-				output: 6,
-				cacheRead: 0.375,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-3.5-turbo": {
-			id: "openai/gpt-3.5-turbo",
-			name: "OpenAI: GPT-3.5 Turbo",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.5,
-				output: 1.5,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 16385,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-3.5-turbo-0613": {
-			id: "openai/gpt-3.5-turbo-0613",
-			name: "OpenAI: GPT-3.5 Turbo (older v0613)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1,
-				output: 2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 4095,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-3.5-turbo-16k": {
-			id: "openai/gpt-3.5-turbo-16k",
-			name: "OpenAI: GPT-3.5 Turbo 16k",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 3,
-				output: 4,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 16385,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4": {
-			id: "openai/gpt-4",
-			name: "OpenAI: GPT-4",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 30,
-				output: 60,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8191,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4-0314": {
-			id: "openai/gpt-4-0314",
-			name: "OpenAI: GPT-4 (older v0314)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 30,
-				output: 60,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8191,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4-1106-preview": {
-			id: "openai/gpt-4-1106-preview",
-			name: "OpenAI: GPT-4 Turbo (older v1106)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 10,
-				output: 30,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4-turbo": {
-			id: "openai/gpt-4-turbo",
-			name: "OpenAI: GPT-4 Turbo",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 10,
-				output: 30,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4-turbo-preview": {
-			id: "openai/gpt-4-turbo-preview",
-			name: "OpenAI: GPT-4 Turbo Preview",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 10,
-				output: 30,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4.1": {
-			id: "openai/gpt-4.1",
-			name: "OpenAI: GPT-4.1",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 8,
-				cacheRead: 0.5,
-				cacheWrite: 0,
-			},
-			contextWindow: 1047576,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4.1-mini": {
-			id: "openai/gpt-4.1-mini",
-			name: "OpenAI: GPT-4.1 Mini",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.39999999999999997,
-				output: 1.5999999999999999,
-				cacheRead: 0.09999999999999999,
-				cacheWrite: 0,
-			},
-			contextWindow: 1047576,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4.1-nano": {
-			id: "openai/gpt-4.1-nano",
-			name: "OpenAI: GPT-4.1 Nano",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.39999999999999997,
-				cacheRead: 0.024999999999999998,
-				cacheWrite: 0,
-			},
-			contextWindow: 1047576,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4o": {
-			id: "openai/gpt-4o",
-			name: "OpenAI: GPT-4o",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2.5,
-				output: 10,
-				cacheRead: 1.25,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4o-2024-05-13": {
-			id: "openai/gpt-4o-2024-05-13",
-			name: "OpenAI: GPT-4o (2024-05-13)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
 			input: ["text", "image"],
 			cost: {
 				input: 5,
-				output: 15,
-				cacheRead: 0,
-				cacheWrite: 0,
+				output: 25,
+				cacheRead: 0.5,
+				cacheWrite: 6.25,
 			},
-			contextWindow: 128000,
-			maxTokens: 4096,
+			contextWindow: 200000,
+			maxTokens: 32000,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-4o-2024-08-06": {
-			id: "openai/gpt-4o-2024-08-06",
-			name: "OpenAI: GPT-4o (2024-08-06)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2.5,
-				output: 10,
-				cacheRead: 1.25,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4o-2024-11-20": {
-			id: "openai/gpt-4o-2024-11-20",
-			name: "OpenAI: GPT-4o (2024-11-20)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2.5,
-				output: 10,
-				cacheRead: 1.25,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4o-audio-preview": {
-			id: "openai/gpt-4o-audio-preview",
-			name: "OpenAI: GPT-4o Audio",
+		"allenai/olmo-3-7b-instruct": {
+			id: "allenai/olmo-3-7b-instruct",
+			name: "AllenAI: Olmo 3 7B Instruct",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 2.5,
-				output: 10,
+				input: 0.09999999999999999,
+				output: 0.19999999999999998,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
-			maxTokens: 16384,
+			contextWindow: 65536,
+			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-4o-mini": {
-			id: "openai/gpt-4o-mini",
-			name: "OpenAI: GPT-4o-mini",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.15,
-				output: 0.6,
-				cacheRead: 0.075,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4o-mini-2024-07-18": {
-			id: "openai/gpt-4o-mini-2024-07-18",
-			name: "OpenAI: GPT-4o-mini (2024-07-18)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.15,
-				output: 0.6,
-				cacheRead: 0.075,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-4o:extended": {
-			id: "openai/gpt-4o:extended",
-			name: "OpenAI: GPT-4o (extended)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 6,
-				output: 18,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-5": {
-			id: "openai/gpt-5",
-			name: "OpenAI: GPT-5",
+		"x-ai/grok-4.1-fast": {
+			id: "x-ai/grok-4.1-fast",
+			name: "xAI: Grok 4.1 Fast",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.125,
+				input: 0.19999999999999998,
+				output: 0.5,
+				cacheRead: 0.049999999999999996,
 				cacheWrite: 0,
 			},
-			contextWindow: 400000,
-			maxTokens: 128000,
+			contextWindow: 2000000,
+			maxTokens: 30000,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-5-codex": {
-			id: "openai/gpt-5-codex",
-			name: "OpenAI: GPT-5 Codex",
+		"google/gemini-3-pro-preview": {
+			id: "google/gemini-3-pro-preview",
+			name: "Google: Gemini 3 Pro Preview",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.125,
-				cacheWrite: 0,
+				input: 2,
+				output: 12,
+				cacheRead: 0.19999999999999998,
+				cacheWrite: 2.375,
 			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-5-image": {
-			id: "openai/gpt-5-image",
-			name: "OpenAI: GPT-5 Image",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 10,
-				output: 10,
-				cacheRead: 1.25,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-5-image-mini": {
-			id: "openai/gpt-5-image-mini",
-			name: "OpenAI: GPT-5 Image Mini",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 2.5,
-				output: 2,
-				cacheRead: 0.25,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-5-mini": {
-			id: "openai/gpt-5-mini",
-			name: "OpenAI: GPT-5 Mini",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.25,
-				output: 2,
-				cacheRead: 0.024999999999999998,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-5-nano": {
-			id: "openai/gpt-5-nano",
-			name: "OpenAI: GPT-5 Nano",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.049999999999999996,
-				output: 0.39999999999999997,
-				cacheRead: 0.005,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-5-pro": {
-			id: "openai/gpt-5-pro",
-			name: "OpenAI: GPT-5 Pro",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 120,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
+			contextWindow: 1048576,
+			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-5.1": {
 			id: "openai/gpt-5.1",
@@ -5203,23 +3486,6 @@ export const MODELS = {
 			contextWindow: 400000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-5.1-codex-max": {
-			id: "openai/gpt-5.1-codex-max",
-			name: "OpenAI: GPT-5.1-Codex-Max",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.25,
-				output: 10,
-				cacheRead: 0.125,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
 		"openai/gpt-5.1-codex-mini": {
 			id: "openai/gpt-5.1-codex-mini",
 			name: "OpenAI: GPT-5.1-Codex-Mini",
@@ -5237,142 +3503,74 @@ export const MODELS = {
 			contextWindow: 400000,
 			maxTokens: 100000,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-5.2": {
-			id: "openai/gpt-5.2",
-			name: "OpenAI: GPT-5.2",
+		"kwaipilot/kat-coder-pro:free": {
+			id: "kwaipilot/kat-coder-pro:free",
+			name: "Kwaipilot: KAT-Coder-Pro V1 (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"moonshotai/kimi-k2-thinking": {
+			id: "moonshotai/kimi-k2-thinking",
+			name: "MoonshotAI: Kimi K2 Thinking",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
-			input: ["text", "image"],
+			input: ["text"],
 			cost: {
-				input: 1.75,
-				output: 14,
-				cacheRead: 0.175,
+				input: 0.39999999999999997,
+				output: 1.75,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 400000,
-			maxTokens: 128000,
+			contextWindow: 262144,
+			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-5.2-chat": {
-			id: "openai/gpt-5.2-chat",
-			name: "OpenAI: GPT-5.2 Chat",
+		"amazon/nova-premier-v1": {
+			id: "amazon/nova-premier-v1",
+			name: "Amazon: Nova Premier 1.0",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 1.75,
-				output: 14,
-				cacheRead: 0.175,
+				input: 2.5,
+				output: 12.5,
+				cacheRead: 0.625,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
-			maxTokens: 16384,
+			contextWindow: 1000000,
+			maxTokens: 32000,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-5.2-pro": {
-			id: "openai/gpt-5.2-pro",
-			name: "OpenAI: GPT-5.2 Pro",
+		"mistralai/voxtral-small-24b-2507": {
+			id: "mistralai/voxtral-small-24b-2507",
+			name: "Mistral: Voxtral Small 24B 2507",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 21,
-				output: 168,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 400000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-oss-120b": {
-			id: "openai/gpt-oss-120b",
-			name: "OpenAI: gpt-oss-120b",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
+			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.039,
-				output: 0.19,
+				input: 0.09999999999999999,
+				output: 0.3,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
+			contextWindow: 32000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-oss-120b:exacto": {
-			id: "openai/gpt-oss-120b:exacto",
-			name: "OpenAI: gpt-oss-120b (exacto)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.039,
-				output: 0.19,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-oss-120b:free": {
-			id: "openai/gpt-oss-120b:free",
-			name: "OpenAI: gpt-oss-120b (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-oss-20b": {
-			id: "openai/gpt-oss-20b",
-			name: "OpenAI: gpt-oss-20b",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.03,
-				output: 0.14,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-oss-20b:free": {
-			id: "openai/gpt-oss-20b:free",
-			name: "OpenAI: gpt-oss-20b (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
 		"openai/gpt-oss-safeguard-20b": {
 			id: "openai/gpt-oss-safeguard-20b",
 			name: "OpenAI: gpt-oss-safeguard-20b",
@@ -5390,39 +3588,141 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"openai/o1": {
-			id: "openai/o1",
-			name: "OpenAI: o1",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 60,
-				cacheRead: 7.5,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-completions">,
-		"openai/o3": {
-			id: "openai/o3",
-			name: "OpenAI: o3",
+		"nvidia/nemotron-nano-12b-v2-vl:free": {
+			id: "nvidia/nemotron-nano-12b-v2-vl:free",
+			name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 2,
-				output: 8,
-				cacheRead: 0.5,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
+			contextWindow: 128000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"minimax/minimax-m2": {
+			id: "minimax/minimax-m2",
+			name: "MiniMax: MiniMax M2",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.19999999999999998,
+				output: 1,
+				cacheRead: 0.03,
+				cacheWrite: 0,
+			},
+			contextWindow: 196608,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"deepcogito/cogito-v2-preview-llama-405b": {
+			id: "deepcogito/cogito-v2-preview-llama-405b",
+			name: "Deep Cogito: Cogito V2 Preview Llama 405B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 3.5,
+				output: 3.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-5-image-mini": {
+			id: "openai/gpt-5-image-mini",
+			name: "OpenAI: GPT-5 Image Mini",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2.5,
+				output: 2,
+				cacheRead: 0.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"anthropic/claude-haiku-4.5": {
+			id: "anthropic/claude-haiku-4.5",
+			name: "Anthropic: Claude Haiku 4.5",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1,
+				output: 5,
+				cacheRead: 0.09999999999999999,
+				cacheWrite: 1.25,
+			},
 			contextWindow: 200000,
-			maxTokens: 100000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-vl-8b-thinking": {
+			id: "qwen/qwen3-vl-8b-thinking",
+			name: "Qwen: Qwen3 VL 8B Thinking",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.18,
+				output: 2.0999999999999996,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-vl-8b-instruct": {
+			id: "qwen/qwen3-vl-8b-instruct",
+			name: "Qwen: Qwen3 VL 8B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.064,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-5-image": {
+			id: "openai/gpt-5-image",
+			name: "OpenAI: GPT-5 Image",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 10,
+				output: 10,
+				cacheRead: 1.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
 		"openai/o3-deep-research": {
 			id: "openai/o3-deep-research",
@@ -5441,74 +3741,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 100000,
 		} satisfies Model<"openai-completions">,
-		"openai/o3-mini": {
-			id: "openai/o3-mini",
-			name: "OpenAI: o3 Mini",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1.1,
-				output: 4.4,
-				cacheRead: 0.55,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-completions">,
-		"openai/o3-mini-high": {
-			id: "openai/o3-mini-high",
-			name: "OpenAI: o3 Mini High",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1.1,
-				output: 4.4,
-				cacheRead: 0.55,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-completions">,
-		"openai/o3-pro": {
-			id: "openai/o3-pro",
-			name: "OpenAI: o3 Pro",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 20,
-				output: 80,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-completions">,
-		"openai/o4-mini": {
-			id: "openai/o4-mini",
-			name: "OpenAI: o4 Mini",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.1,
-				output: 4.4,
-				cacheRead: 0.275,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-completions">,
 		"openai/o4-mini-deep-research": {
 			id: "openai/o4-mini-deep-research",
 			name: "OpenAI: o4 Mini Deep Research",
@@ -5526,548 +3758,21 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 100000,
 		} satisfies Model<"openai-completions">,
-		"openai/o4-mini-high": {
-			id: "openai/o4-mini-high",
-			name: "OpenAI: o4 Mini High",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 1.1,
-				output: 4.4,
-				cacheRead: 0.275,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-completions">,
-		"openrouter/auto": {
-			id: "openrouter/auto",
-			name: "OpenRouter: Auto Router",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 30000,
-		} satisfies Model<"openai-completions">,
-		"prime-intellect/intellect-3": {
-			id: "prime-intellect/intellect-3",
-			name: "Prime Intellect: INTELLECT-3",
+		"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
+			id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
+			name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.19999999999999998,
-				output: 1.1,
+				input: 0.09999999999999999,
+				output: 0.39999999999999997,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen-2.5-72b-instruct": {
-			id: "qwen/qwen-2.5-72b-instruct",
-			name: "Qwen2.5 72B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.12,
-				output: 0.39,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen-max": {
-			id: "qwen/qwen-max",
-			name: "Qwen: Qwen-Max ",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1.5999999999999999,
-				output: 6.3999999999999995,
-				cacheRead: 0.64,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen-plus": {
-			id: "qwen/qwen-plus",
-			name: "Qwen: Qwen-Plus",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.39999999999999997,
-				output: 1.2,
-				cacheRead: 0.16,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen-plus-2025-07-28": {
-			id: "qwen/qwen-plus-2025-07-28",
-			name: "Qwen: Qwen Plus 0728",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.39999999999999997,
-				output: 1.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen-plus-2025-07-28:thinking": {
-			id: "qwen/qwen-plus-2025-07-28:thinking",
-			name: "Qwen: Qwen Plus 0728 (thinking)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.39999999999999997,
-				output: 4,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen-turbo": {
-			id: "qwen/qwen-turbo",
-			name: "Qwen: Qwen-Turbo",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.049999999999999996,
-				output: 0.19999999999999998,
-				cacheRead: 0.02,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen-vl-max": {
-			id: "qwen/qwen-vl-max",
-			name: "Qwen: Qwen VL Max",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.7999999999999999,
-				output: 3.1999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-14b": {
-			id: "qwen/qwen3-14b",
-			name: "Qwen: Qwen3 14B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.049999999999999996,
-				output: 0.22,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 40960,
-			maxTokens: 40960,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-235b-a22b": {
-			id: "qwen/qwen3-235b-a22b",
-			name: "Qwen: Qwen3 235B A22B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.18,
-				output: 0.54,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 40960,
-			maxTokens: 40960,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-235b-a22b-2507": {
-			id: "qwen/qwen3-235b-a22b-2507",
-			name: "Qwen: Qwen3 235B A22B Instruct 2507",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.071,
-				output: 0.463,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-235b-a22b-thinking-2507": {
-			id: "qwen/qwen3-235b-a22b-thinking-2507",
-			name: "Qwen: Qwen3 235B A22B Thinking 2507",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.11,
-				output: 0.6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-30b-a3b": {
-			id: "qwen/qwen3-30b-a3b",
-			name: "Qwen: Qwen3 30B A3B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.06,
-				output: 0.22,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 40960,
-			maxTokens: 40960,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-30b-a3b-instruct-2507": {
-			id: "qwen/qwen3-30b-a3b-instruct-2507",
-			name: "Qwen: Qwen3 30B A3B Instruct 2507",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.08,
-				output: 0.33,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-30b-a3b-thinking-2507": {
-			id: "qwen/qwen3-30b-a3b-thinking-2507",
-			name: "Qwen: Qwen3 30B A3B Thinking 2507",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.051,
-				output: 0.33999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-32b": {
-			id: "qwen/qwen3-32b",
-			name: "Qwen: Qwen3 32B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.08,
-				output: 0.24,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 40960,
-			maxTokens: 40960,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-4b:free": {
-			id: "qwen/qwen3-4b:free",
-			name: "Qwen: Qwen3 4B (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 40960,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-8b": {
-			id: "qwen/qwen3-8b",
-			name: "Qwen: Qwen3 8B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.028,
-				output: 0.1104,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 20000,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-coder": {
-			id: "qwen/qwen3-coder",
-			name: "Qwen: Qwen3 Coder 480B A35B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.22,
-				output: 0.95,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-coder-30b-a3b-instruct": {
-			id: "qwen/qwen3-coder-30b-a3b-instruct",
-			name: "Qwen: Qwen3 Coder 30B A3B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.07,
-				output: 0.27,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 160000,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-coder-flash": {
-			id: "qwen/qwen3-coder-flash",
-			name: "Qwen: Qwen3 Coder Flash",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 1.5,
-				cacheRead: 0.08,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-coder-plus": {
-			id: "qwen/qwen3-coder-plus",
-			name: "Qwen: Qwen3 Coder Plus",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1,
-				output: 5,
-				cacheRead: 0.09999999999999999,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-coder:exacto": {
-			id: "qwen/qwen3-coder:exacto",
-			name: "Qwen: Qwen3 Coder 480B A35B (exacto)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.22,
-				output: 1.7999999999999998,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-coder:free": {
-			id: "qwen/qwen3-coder:free",
-			name: "Qwen: Qwen3 Coder 480B A35B (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262000,
-			maxTokens: 262000,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-max": {
-			id: "qwen/qwen3-max",
-			name: "Qwen: Qwen3 Max",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1.2,
-				output: 6,
-				cacheRead: 0.24,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-next-80b-a3b-instruct": {
-			id: "qwen/qwen3-next-80b-a3b-instruct",
-			name: "Qwen: Qwen3 Next 80B A3B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.09,
-				output: 1.1,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-next-80b-a3b-thinking": {
-			id: "qwen/qwen3-next-80b-a3b-thinking",
-			name: "Qwen: Qwen3 Next 80B A3B Thinking",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.12,
-				output: 1.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-vl-235b-a22b-instruct": {
-			id: "qwen/qwen3-vl-235b-a22b-instruct",
-			name: "Qwen: Qwen3 VL 235B A22B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.19999999999999998,
-				output: 1.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-vl-235b-a22b-thinking": {
-			id: "qwen/qwen3-vl-235b-a22b-thinking",
-			name: "Qwen: Qwen3 VL 235B A22B Thinking",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.3,
-				output: 1.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-vl-30b-a3b-instruct": {
-			id: "qwen/qwen3-vl-30b-a3b-instruct",
-			name: "Qwen: Qwen3 VL 30B A3B Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.15,
-				output: 0.6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-vl-30b-a3b-thinking": {
@@ -6087,447 +3792,39 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-vl-8b-instruct": {
-			id: "qwen/qwen3-vl-8b-instruct",
-			name: "Qwen: Qwen3 VL 8B Instruct",
+		"qwen/qwen3-vl-30b-a3b-instruct": {
+			id: "qwen/qwen3-vl-30b-a3b-instruct",
+			name: "Qwen: Qwen3 VL 30B A3B Instruct",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: false,
 			input: ["text", "image"],
-			cost: {
-				input: 0.064,
-				output: 0.39999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwen3-vl-8b-thinking": {
-			id: "qwen/qwen3-vl-8b-thinking",
-			name: "Qwen: Qwen3 VL 8B Thinking",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.18,
-				output: 2.0999999999999996,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
-		"qwen/qwq-32b": {
-			id: "qwen/qwq-32b",
-			name: "Qwen: QwQ 32B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
 			cost: {
 				input: 0.15,
-				output: 0.39999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"relace/relace-search": {
-			id: "relace/relace-search",
-			name: "Relace: Relace Search",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1,
-				output: 3,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"sao10k/l3-euryale-70b": {
-			id: "sao10k/l3-euryale-70b",
-			name: "Sao10k: Llama 3 Euryale 70B v2.1",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1.48,
-				output: 1.48,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"sao10k/l3.1-euryale-70b": {
-			id: "sao10k/l3.1-euryale-70b",
-			name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.65,
-				output: 0.75,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"stepfun-ai/step3": {
-			id: "stepfun-ai/step3",
-			name: "StepFun: Step3",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.5700000000000001,
-				output: 1.42,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 65536,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"thedrummer/rocinante-12b": {
-			id: "thedrummer/rocinante-12b",
-			name: "TheDrummer: Rocinante 12B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.16999999999999998,
-				output: 0.43,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"thedrummer/unslopnemo-12b": {
-			id: "thedrummer/unslopnemo-12b",
-			name: "TheDrummer: UnslopNemo 12B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.39999999999999997,
-				output: 0.39999999999999997,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"tngtech/deepseek-r1t2-chimera": {
-			id: "tngtech/deepseek-r1t2-chimera",
-			name: "TNG: DeepSeek R1T2 Chimera",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 1.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 163840,
-		} satisfies Model<"openai-completions">,
-		"tngtech/tng-r1t-chimera": {
-			id: "tngtech/tng-r1t-chimera",
-			name: "TNG: R1T Chimera",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 1.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"tngtech/tng-r1t-chimera:free": {
-			id: "tngtech/tng-r1t-chimera:free",
-			name: "TNG: R1T Chimera (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 163840,
-			maxTokens: 163840,
-		} satisfies Model<"openai-completions">,
-		"x-ai/grok-3": {
-			id: "x-ai/grok-3",
-			name: "xAI: Grok 3",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.75,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"x-ai/grok-3-beta": {
-			id: "x-ai/grok-3-beta",
-			name: "xAI: Grok 3 Beta",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.75,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"x-ai/grok-3-mini": {
-			id: "x-ai/grok-3-mini",
-			name: "xAI: Grok 3 Mini",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 0.5,
-				cacheRead: 0.075,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"x-ai/grok-3-mini-beta": {
-			id: "x-ai/grok-3-mini-beta",
-			name: "xAI: Grok 3 Mini Beta",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 0.5,
-				cacheRead: 0.075,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"x-ai/grok-4": {
-			id: "x-ai/grok-4",
-			name: "xAI: Grok 4",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.75,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"x-ai/grok-4-fast": {
-			id: "x-ai/grok-4-fast",
-			name: "xAI: Grok 4 Fast",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.19999999999999998,
-				output: 0.5,
-				cacheRead: 0.049999999999999996,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 30000,
-		} satisfies Model<"openai-completions">,
-		"x-ai/grok-4.1-fast": {
-			id: "x-ai/grok-4.1-fast",
-			name: "xAI: Grok 4.1 Fast",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.19999999999999998,
-				output: 0.5,
-				cacheRead: 0.049999999999999996,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 30000,
-		} satisfies Model<"openai-completions">,
-		"x-ai/grok-code-fast-1": {
-			id: "x-ai/grok-code-fast-1",
-			name: "xAI: Grok Code Fast 1",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.19999999999999998,
-				output: 1.5,
-				cacheRead: 0.02,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 10000,
-		} satisfies Model<"openai-completions">,
-		"xiaomi/mimo-v2-flash:free": {
-			id: "xiaomi/mimo-v2-flash:free",
-			name: "Xiaomi: MiMo-V2-Flash (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
+				output: 0.6,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"z-ai/glm-4-32b": {
-			id: "z-ai/glm-4-32b",
-			name: "Z.AI: GLM 4 32B ",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"z-ai/glm-4.5": {
-			id: "z-ai/glm-4.5",
-			name: "Z.AI: GLM 4.5",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.35,
-				output: 1.55,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
-		"z-ai/glm-4.5-air": {
-			id: "z-ai/glm-4.5-air",
-			name: "Z.AI: GLM 4.5 Air",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.10400000000000001,
-				output: 0.6799999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 98304,
-		} satisfies Model<"openai-completions">,
-		"z-ai/glm-4.5-air:free": {
-			id: "z-ai/glm-4.5-air:free",
-			name: "Z.AI: GLM 4.5 Air (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
-		"z-ai/glm-4.5v": {
-			id: "z-ai/glm-4.5v",
-			name: "Z.AI: GLM 4.5V",
+		"openai/gpt-5-pro": {
+			id: "openai/gpt-5-pro",
+			name: "OpenAI: GPT-5 Pro",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.48,
-				output: 1.44,
-				cacheRead: 0.088,
+				input: 15,
+				output: 120,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 65536,
-			maxTokens: 16384,
+			contextWindow: 400000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
 		"z-ai/glm-4.6": {
 			id: "z-ai/glm-4.6",
@@ -6563,461 +3860,216 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
-		"z-ai/glm-4.6v": {
-			id: "z-ai/glm-4.6v",
-			name: "Z.AI: GLM 4.6V",
+		"anthropic/claude-sonnet-4.5": {
+			id: "anthropic/claude-sonnet-4.5",
+			name: "Anthropic: Claude Sonnet 4.5",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.3,
-				output: 0.8999999999999999,
-				cacheRead: 0.049999999999999996,
-				cacheWrite: 0,
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
 			},
-			contextWindow: 131072,
-			maxTokens: 24000,
+			contextWindow: 1000000,
+			maxTokens: 64000,
 		} satisfies Model<"openai-completions">,
-		"z-ai/glm-4.7": {
-			id: "z-ai/glm-4.7",
-			name: "Z.AI: GLM 4.7",
+		"deepseek/deepseek-v3.2-exp": {
+			id: "deepseek/deepseek-v3.2-exp",
+			name: "DeepSeek: DeepSeek V3.2 Exp",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.39999999999999997,
-				output: 1.5,
+				input: 0.21,
+				output: 0.32,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 202752,
-			maxTokens: 65535,
+			contextWindow: 163840,
+			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-	},
-	"xai": {
-		"grok-2": {
-			id: "grok-2",
-			name: "Grok 2",
+		"google/gemini-2.5-flash-preview-09-2025": {
+			id: "google/gemini-2.5-flash-preview-09-2025",
+			name: "Google: Gemini 2.5 Flash Preview 09-2025",
 			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 2,
-				output: 10,
-				cacheRead: 2,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"grok-2-1212": {
-			id: "grok-2-1212",
-			name: "Grok 2 (1212)",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 2,
-				output: 10,
-				cacheRead: 2,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"grok-2-latest": {
-			id: "grok-2-latest",
-			name: "Grok 2 Latest",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 2,
-				output: 10,
-				cacheRead: 2,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"grok-2-vision": {
-			id: "grok-2-vision",
-			name: "Grok 2 Vision",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 10,
-				cacheRead: 2,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"grok-2-vision-1212": {
-			id: "grok-2-vision-1212",
-			name: "Grok 2 Vision (1212)",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 10,
-				cacheRead: 2,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"grok-2-vision-latest": {
-			id: "grok-2-vision-latest",
-			name: "Grok 2 Vision Latest",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 10,
-				cacheRead: 2,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"grok-3": {
-			id: "grok-3",
-			name: "Grok 3",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.75,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"grok-3-fast": {
-			id: "grok-3-fast",
-			name: "Grok 3 Fast",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 5,
-				output: 25,
-				cacheRead: 1.25,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"grok-3-fast-latest": {
-			id: "grok-3-fast-latest",
-			name: "Grok 3 Fast Latest",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 5,
-				output: 25,
-				cacheRead: 1.25,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"grok-3-latest": {
-			id: "grok-3-latest",
-			name: "Grok 3 Latest",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.75,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"grok-3-mini": {
-			id: "grok-3-mini",
-			name: "Grok 3 Mini",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
-			input: ["text"],
+			input: ["text", "image"],
 			cost: {
 				input: 0.3,
-				output: 0.5,
+				output: 2.5,
 				cacheRead: 0.075,
-				cacheWrite: 0,
+				cacheWrite: 0.3833,
 			},
-			contextWindow: 131072,
-			maxTokens: 8192,
+			contextWindow: 1048576,
+			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"grok-3-mini-fast": {
-			id: "grok-3-mini-fast",
-			name: "Grok 3 Mini Fast",
+		"google/gemini-2.5-flash-lite-preview-09-2025": {
+			id: "google/gemini-2.5-flash-lite-preview-09-2025",
+			name: "Google: Gemini 2.5 Flash Lite Preview 09-2025",
 			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
-			input: ["text"],
+			input: ["text", "image"],
 			cost: {
-				input: 0.6,
-				output: 4,
-				cacheRead: 0.15,
+				input: 0.09999999999999999,
+				output: 0.39999999999999997,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 8192,
+			contextWindow: 1048576,
+			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"grok-3-mini-fast-latest": {
-			id: "grok-3-mini-fast-latest",
-			name: "Grok 3 Mini Fast Latest",
+		"qwen/qwen3-vl-235b-a22b-thinking": {
+			id: "qwen/qwen3-vl-235b-a22b-thinking",
+			name: "Qwen: Qwen3 VL 235B A22B Thinking",
 			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.6,
-				output: 4,
-				cacheRead: 0.15,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"grok-3-mini-latest": {
-			id: "grok-3-mini-latest",
-			name: "Grok 3 Mini Latest",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: true,
-			input: ["text"],
+			input: ["text", "image"],
 			cost: {
 				input: 0.3,
-				output: 0.5,
-				cacheRead: 0.075,
+				output: 1.2,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 8192,
+			contextWindow: 262144,
+			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
-		"grok-4": {
-			id: "grok-4",
-			name: "Grok 4",
+		"qwen/qwen3-vl-235b-a22b-instruct": {
+			id: "qwen/qwen3-vl-235b-a22b-instruct",
+			name: "Qwen: Qwen3 VL 235B A22B Instruct",
 			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: true,
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.19999999999999998,
+				output: 1.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-max": {
+			id: "qwen/qwen3-max",
+			name: "Qwen: Qwen3 Max",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.75,
+				input: 1.2,
+				output: 6,
+				cacheRead: 0.24,
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
-			maxTokens: 64000,
+			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
-		"grok-4-1-fast": {
-			id: "grok-4-1-fast",
-			name: "Grok 4.1 Fast",
+		"qwen/qwen3-coder-plus": {
+			id: "qwen/qwen3-coder-plus",
+			name: "Qwen: Qwen3 Coder Plus",
 			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.2,
-				output: 0.5,
-				cacheRead: 0.05,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 30000,
-		} satisfies Model<"openai-completions">,
-		"grok-4-1-fast-non-reasoning": {
-			id: "grok-4-1-fast-non-reasoning",
-			name: "Grok 4.1 Fast (Non-Reasoning)",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.2,
-				output: 0.5,
-				cacheRead: 0.05,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 30000,
-		} satisfies Model<"openai-completions">,
-		"grok-4-fast": {
-			id: "grok-4-fast",
-			name: "Grok 4 Fast",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.2,
-				output: 0.5,
-				cacheRead: 0.05,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 30000,
-		} satisfies Model<"openai-completions">,
-		"grok-4-fast-non-reasoning": {
-			id: "grok-4-fast-non-reasoning",
-			name: "Grok 4 Fast (Non-Reasoning)",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.2,
-				output: 0.5,
-				cacheRead: 0.05,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 30000,
-		} satisfies Model<"openai-completions">,
-		"grok-beta": {
-			id: "grok-beta",
-			name: "Grok Beta",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 5,
-				output: 15,
-				cacheRead: 5,
+				input: 1,
+				output: 5,
+				cacheRead: 0.09999999999999999,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
+			contextWindow: 128000,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-5-codex": {
+			id: "openai/gpt-5-codex",
+			name: "OpenAI: GPT-5 Codex",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"deepseek/deepseek-v3.1-terminus:exacto": {
+			id: "deepseek/deepseek-v3.1-terminus:exacto",
+			name: "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.21,
+				output: 0.7899999999999999,
+				cacheRead: 0.16799999999999998,
+				cacheWrite: 0,
+			},
+			contextWindow: 163840,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"grok-code-fast-1": {
-			id: "grok-code-fast-1",
-			name: "Grok Code Fast 1",
+		"deepseek/deepseek-v3.1-terminus": {
+			id: "deepseek/deepseek-v3.1-terminus",
+			name: "DeepSeek: DeepSeek V3.1 Terminus",
 			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.2,
-				output: 1.5,
-				cacheRead: 0.02,
+				input: 0.21,
+				output: 0.7899999999999999,
+				cacheRead: 0.16799999999999998,
 				cacheWrite: 0,
 			},
-			contextWindow: 256000,
-			maxTokens: 10000,
-		} satisfies Model<"openai-completions">,
-		"grok-vision-beta": {
-			id: "grok-vision-beta",
-			name: "Grok Vision Beta",
-			api: "openai-completions",
-			provider: "xai",
-			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 5,
-				output: 15,
-				cacheRead: 5,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
+			contextWindow: 163840,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-	},
-	"zai": {
-		"glm-4.5": {
-			id: "glm-4.5",
-			name: "GLM-4.5",
+		"x-ai/grok-4-fast": {
+			id: "x-ai/grok-4-fast",
+			name: "xAI: Grok 4 Fast",
 			api: "openai-completions",
-			provider: "zai",
-			baseUrl: "https://api.z.ai/api/coding/paas/v4",
-			compat: {"supportsDeveloperRole":false},
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
-			input: ["text"],
+			input: ["text", "image"],
 			cost: {
-				input: 0.6,
-				output: 2.2,
-				cacheRead: 0.11,
+				input: 0.19999999999999998,
+				output: 0.5,
+				cacheRead: 0.049999999999999996,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 98304,
+			contextWindow: 2000000,
+			maxTokens: 30000,
 		} satisfies Model<"openai-completions">,
-		"glm-4.5-air": {
-			id: "glm-4.5-air",
-			name: "GLM-4.5-Air",
+		"alibaba/tongyi-deepresearch-30b-a3b:free": {
+			id: "alibaba/tongyi-deepresearch-30b-a3b:free",
+			name: "Tongyi DeepResearch 30B A3B (free)",
 			api: "openai-completions",
-			provider: "zai",
-			baseUrl: "https://api.z.ai/api/coding/paas/v4",
-			compat: {"supportsDeveloperRole":false},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.2,
-				output: 1.1,
-				cacheRead: 0.03,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 98304,
-		} satisfies Model<"openai-completions">,
-		"glm-4.5-flash": {
-			id: "glm-4.5-flash",
-			name: "GLM-4.5-Flash",
-			api: "openai-completions",
-			provider: "zai",
-			baseUrl: "https://api.z.ai/api/coding/paas/v4",
-			compat: {"supportsDeveloperRole":false},
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
@@ -7027,79 +4079,3020 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 98304,
+			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
-		"glm-4.5v": {
-			id: "glm-4.5v",
-			name: "GLM-4.5V",
+		"alibaba/tongyi-deepresearch-30b-a3b": {
+			id: "alibaba/tongyi-deepresearch-30b-a3b",
+			name: "Tongyi DeepResearch 30B A3B",
 			api: "openai-completions",
-			provider: "zai",
-			baseUrl: "https://api.z.ai/api/coding/paas/v4",
-			compat: {"supportsDeveloperRole":false},
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.6,
-				output: 1.8,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 64000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"glm-4.6": {
-			id: "glm-4.6",
-			name: "GLM-4.6",
-			api: "openai-completions",
-			provider: "zai",
-			baseUrl: "https://api.z.ai/api/coding/paas/v4",
-			compat: {"supportsDeveloperRole":false},
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.6,
-				output: 2.2,
-				cacheRead: 0.11,
+				input: 0.09,
+				output: 0.39999999999999997,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 204800,
+			contextWindow: 131072,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
-		"glm-4.6v": {
-			id: "glm-4.6v",
-			name: "GLM-4.6V",
+		"qwen/qwen3-coder-flash": {
+			id: "qwen/qwen3-coder-flash",
+			name: "Qwen: Qwen3 Coder Flash",
 			api: "openai-completions",
-			provider: "zai",
-			baseUrl: "https://api.z.ai/api/coding/paas/v4",
-			compat: {"supportsDeveloperRole":false},
-			reasoning: true,
-			input: ["text", "image"],
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
 			cost: {
 				input: 0.3,
-				output: 0.9,
+				output: 1.5,
+				cacheRead: 0.08,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-next-80b-a3b-thinking": {
+			id: "qwen/qwen3-next-80b-a3b-thinking",
+			name: "Qwen: Qwen3 Next 80B A3B Thinking",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.12,
+				output: 1.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-next-80b-a3b-instruct": {
+			id: "qwen/qwen3-next-80b-a3b-instruct",
+			name: "Qwen: Qwen3 Next 80B A3B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.09,
+				output: 1.1,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen-plus-2025-07-28": {
+			id: "qwen/qwen-plus-2025-07-28",
+			name: "Qwen: Qwen Plus 0728",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 1.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen-plus-2025-07-28:thinking": {
+			id: "qwen/qwen-plus-2025-07-28:thinking",
+			name: "Qwen: Qwen Plus 0728 (thinking)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"nvidia/nemotron-nano-9b-v2:free": {
+			id: "nvidia/nemotron-nano-9b-v2:free",
+			name: "NVIDIA: Nemotron Nano 9B V2 (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
-			maxTokens: 32768,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"glm-4.7": {
-			id: "glm-4.7",
-			name: "GLM-4.7",
+		"nvidia/nemotron-nano-9b-v2": {
+			id: "nvidia/nemotron-nano-9b-v2",
+			name: "NVIDIA: Nemotron Nano 9B V2",
 			api: "openai-completions",
-			provider: "zai",
-			baseUrl: "https://api.z.ai/api/coding/paas/v4",
-			compat: {"supportsDeveloperRole":false},
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.6,
-				output: 2.2,
-				cacheRead: 0.11,
+				input: 0.04,
+				output: 0.16,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 204800,
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"moonshotai/kimi-k2-0905": {
+			id: "moonshotai/kimi-k2-0905",
+			name: "MoonshotAI: Kimi K2 0905",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.39,
+				output: 1.9,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"moonshotai/kimi-k2-0905:exacto": {
+			id: "moonshotai/kimi-k2-0905:exacto",
+			name: "MoonshotAI: Kimi K2 0905 (exacto)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"deepcogito/cogito-v2-preview-llama-70b": {
+			id: "deepcogito/cogito-v2-preview-llama-70b",
+			name: "Deep Cogito: Cogito V2 Preview Llama 70B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.88,
+				output: 0.88,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"deepcogito/cogito-v2-preview-llama-109b-moe": {
+			id: "deepcogito/cogito-v2-preview-llama-109b-moe",
+			name: "Cogito V2 Preview Llama 109B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.18,
+				output: 0.59,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32767,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"stepfun-ai/step3": {
+			id: "stepfun-ai/step3",
+			name: "StepFun: Step3",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.5700000000000001,
+				output: 1.42,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 65536,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-30b-a3b-thinking-2507": {
+			id: "qwen/qwen3-30b-a3b-thinking-2507",
+			name: "Qwen: Qwen3 30B A3B Thinking 2507",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.051,
+				output: 0.33999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"x-ai/grok-code-fast-1": {
+			id: "x-ai/grok-code-fast-1",
+			name: "xAI: Grok Code Fast 1",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.19999999999999998,
+				output: 1.5,
+				cacheRead: 0.02,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 10000,
+		} satisfies Model<"openai-completions">,
+		"nousresearch/hermes-4-70b": {
+			id: "nousresearch/hermes-4-70b",
+			name: "Nous: Hermes 4 70B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.11,
+				output: 0.38,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"nousresearch/hermes-4-405b": {
+			id: "nousresearch/hermes-4-405b",
+			name: "Nous: Hermes 4 405B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"deepseek/deepseek-chat-v3.1": {
+			id: "deepseek/deepseek-chat-v3.1",
+			name: "DeepSeek: DeepSeek V3.1",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.15,
+				output: 0.75,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 7168,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4o-audio-preview": {
+			id: "openai/gpt-4o-audio-preview",
+			name: "OpenAI: GPT-4o Audio",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2.5,
+				output: 10,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-medium-3.1": {
+			id: "mistralai/mistral-medium-3.1",
+			name: "Mistral: Mistral Medium 3.1",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"baidu/ernie-4.5-21b-a3b": {
+			id: "baidu/ernie-4.5-21b-a3b",
+			name: "Baidu: ERNIE 4.5 21B A3B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.056,
+				output: 0.224,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 120000,
+			maxTokens: 8000,
+		} satisfies Model<"openai-completions">,
+		"baidu/ernie-4.5-vl-28b-a3b": {
+			id: "baidu/ernie-4.5-vl-28b-a3b",
+			name: "Baidu: ERNIE 4.5 VL 28B A3B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.112,
+				output: 0.448,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 30000,
+			maxTokens: 8000,
+		} satisfies Model<"openai-completions">,
+		"z-ai/glm-4.5v": {
+			id: "z-ai/glm-4.5v",
+			name: "Z.AI: GLM 4.5V",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.48,
+				output: 1.44,
+				cacheRead: 0.088,
+				cacheWrite: 0,
+			},
+			contextWindow: 65536,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"ai21/jamba-mini-1.7": {
+			id: "ai21/jamba-mini-1.7",
+			name: "AI21: Jamba Mini 1.7",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.19999999999999998,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"ai21/jamba-large-1.7": {
+			id: "ai21/jamba-large-1.7",
+			name: "AI21: Jamba Large 1.7",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 8,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-5": {
+			id: "openai/gpt-5",
+			name: "OpenAI: GPT-5",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-5-mini": {
+			id: "openai/gpt-5-mini",
+			name: "OpenAI: GPT-5 Mini",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 2,
+				cacheRead: 0.024999999999999998,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-5-nano": {
+			id: "openai/gpt-5-nano",
+			name: "OpenAI: GPT-5 Nano",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.049999999999999996,
+				output: 0.39999999999999997,
+				cacheRead: 0.005,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-oss-120b:free": {
+			id: "openai/gpt-oss-120b:free",
+			name: "OpenAI: gpt-oss-120b (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-oss-120b": {
+			id: "openai/gpt-oss-120b",
+			name: "OpenAI: gpt-oss-120b",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.039,
+				output: 0.19,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-oss-120b:exacto": {
+			id: "openai/gpt-oss-120b:exacto",
+			name: "OpenAI: gpt-oss-120b (exacto)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.039,
+				output: 0.19,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-oss-20b:free": {
+			id: "openai/gpt-oss-20b:free",
+			name: "OpenAI: gpt-oss-20b (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-oss-20b": {
+			id: "openai/gpt-oss-20b",
+			name: "OpenAI: gpt-oss-20b",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.03,
+				output: 0.14,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"anthropic/claude-opus-4.1": {
+			id: "anthropic/claude-opus-4.1",
+			name: "Anthropic: Claude Opus 4.1",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 15,
+				output: 75,
+				cacheRead: 1.5,
+				cacheWrite: 18.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/codestral-2508": {
+			id: "mistralai/codestral-2508",
+			name: "Mistral: Codestral 2508",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 0.8999999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-coder-30b-a3b-instruct": {
+			id: "qwen/qwen3-coder-30b-a3b-instruct",
+			name: "Qwen: Qwen3 Coder 30B A3B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.07,
+				output: 0.27,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 160000,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-30b-a3b-instruct-2507": {
+			id: "qwen/qwen3-30b-a3b-instruct-2507",
+			name: "Qwen: Qwen3 30B A3B Instruct 2507",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.08,
+				output: 0.33,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"z-ai/glm-4.5": {
+			id: "z-ai/glm-4.5",
+			name: "Z.AI: GLM 4.5",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.35,
+				output: 1.55,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"z-ai/glm-4.5-air:free": {
+			id: "z-ai/glm-4.5-air:free",
+			name: "Z.AI: GLM 4.5 Air (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"z-ai/glm-4.5-air": {
+			id: "z-ai/glm-4.5-air",
+			name: "Z.AI: GLM 4.5 Air",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.10400000000000001,
+				output: 0.6799999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 98304,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-235b-a22b-thinking-2507": {
+			id: "qwen/qwen3-235b-a22b-thinking-2507",
+			name: "Qwen: Qwen3 235B A22B Thinking 2507",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.11,
+				output: 0.6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"z-ai/glm-4-32b": {
+			id: "z-ai/glm-4-32b",
+			name: "Z.AI: GLM 4 32B ",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.09999999999999999,
+				output: 0.09999999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-coder:free": {
+			id: "qwen/qwen3-coder:free",
+			name: "Qwen: Qwen3 Coder 480B A35B (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262000,
+			maxTokens: 262000,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-coder": {
+			id: "qwen/qwen3-coder",
+			name: "Qwen: Qwen3 Coder 480B A35B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.22,
+				output: 0.95,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-coder:exacto": {
+			id: "qwen/qwen3-coder:exacto",
+			name: "Qwen: Qwen3 Coder 480B A35B (exacto)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.22,
+				output: 1.7999999999999998,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"google/gemini-2.5-flash-lite": {
+			id: "google/gemini-2.5-flash-lite",
+			name: "Google: Gemini 2.5 Flash Lite",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.09999999999999999,
+				output: 0.39999999999999997,
+				cacheRead: 0.01,
+				cacheWrite: 0.18330000000000002,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-235b-a22b-2507": {
+			id: "qwen/qwen3-235b-a22b-2507",
+			name: "Qwen: Qwen3 235B A22B Instruct 2507",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.071,
+				output: 0.463,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"moonshotai/kimi-k2": {
+			id: "moonshotai/kimi-k2",
+			name: "MoonshotAI: Kimi K2 0711",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.456,
+				output: 1.8399999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"mistralai/devstral-medium": {
+			id: "mistralai/devstral-medium",
+			name: "Mistral: Devstral Medium",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/devstral-small": {
+			id: "mistralai/devstral-small",
+			name: "Mistral: Devstral Small 1.1",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.07,
+				output: 0.28,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"x-ai/grok-4": {
+			id: "x-ai/grok-4",
+			name: "xAI: Grok 4",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.75,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"tngtech/deepseek-r1t2-chimera": {
+			id: "tngtech/deepseek-r1t2-chimera",
+			name: "TNG: DeepSeek R1T2 Chimera",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 163840,
+			maxTokens: 163840,
+		} satisfies Model<"openai-completions">,
+		"inception/mercury": {
+			id: "inception/mercury",
+			name: "Inception: Mercury",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.25,
+				output: 1,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-small-3.2-24b-instruct": {
+			id: "mistralai/mistral-small-3.2-24b-instruct",
+			name: "Mistral: Mistral Small 3.2 24B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.06,
+				output: 0.18,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"minimax/minimax-m1": {
+			id: "minimax/minimax-m1",
+			name: "MiniMax: MiniMax M1",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 2.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 40000,
+		} satisfies Model<"openai-completions">,
+		"google/gemini-2.5-flash": {
+			id: "google/gemini-2.5-flash",
+			name: "Google: Gemini 2.5 Flash",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.3,
+				output: 2.5,
+				cacheRead: 0.03,
+				cacheWrite: 0.3833,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"openai-completions">,
+		"google/gemini-2.5-pro": {
+			id: "google/gemini-2.5-pro",
+			name: "Google: Gemini 2.5 Pro",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 1.625,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"openai/o3-pro": {
+			id: "openai/o3-pro",
+			name: "OpenAI: o3 Pro",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 20,
+				output: 80,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-completions">,
+		"x-ai/grok-3-mini": {
+			id: "x-ai/grok-3-mini",
+			name: "xAI: Grok 3 Mini",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 0.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"x-ai/grok-3": {
+			id: "x-ai/grok-3",
+			name: "xAI: Grok 3",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.75,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"google/gemini-2.5-pro-preview": {
+			id: "google/gemini-2.5-pro-preview",
+			name: "Google: Gemini 2.5 Pro Preview 06-05",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.31,
+				cacheWrite: 1.625,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"deepseek/deepseek-r1-0528": {
+			id: "deepseek/deepseek-r1-0528",
+			name: "DeepSeek: R1 0528",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 1.75,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 163840,
+			maxTokens: 163840,
+		} satisfies Model<"openai-completions">,
+		"anthropic/claude-opus-4": {
+			id: "anthropic/claude-opus-4",
+			name: "Anthropic: Claude Opus 4",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 15,
+				output: 75,
+				cacheRead: 1.5,
+				cacheWrite: 18.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 32000,
+		} satisfies Model<"openai-completions">,
+		"anthropic/claude-sonnet-4": {
+			id: "anthropic/claude-sonnet-4",
+			name: "Anthropic: Claude Sonnet 4",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 1000000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"openai/codex-mini": {
+			id: "openai/codex-mini",
+			name: "OpenAI: Codex Mini",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.5,
+				output: 6,
+				cacheRead: 0.375,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-completions">,
+		"nousresearch/deephermes-3-mistral-24b-preview": {
+			id: "nousresearch/deephermes-3-mistral-24b-preview",
+			name: "Nous: DeepHermes 3 Mistral 24B Preview",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.02,
+				output: 0.09999999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-medium-3": {
+			id: "mistralai/mistral-medium-3",
+			name: "Mistral: Mistral Medium 3",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"google/gemini-2.5-pro-preview-05-06": {
+			id: "google/gemini-2.5-pro-preview-05-06",
+			name: "Google: Gemini 2.5 Pro Preview 05-06",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.31,
+				cacheWrite: 1.625,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"openai-completions">,
+		"arcee-ai/virtuoso-large": {
+			id: "arcee-ai/virtuoso-large",
+			name: "Arcee AI: Virtuoso Large",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.75,
+				output: 1.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"inception/mercury-coder": {
+			id: "inception/mercury-coder",
+			name: "Inception: Mercury Coder",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.25,
+				output: 1,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-4b:free": {
+			id: "qwen/qwen3-4b:free",
+			name: "Qwen: Qwen3 4B (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 40960,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-30b-a3b": {
+			id: "qwen/qwen3-30b-a3b",
+			name: "Qwen: Qwen3 30B A3B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.06,
+				output: 0.22,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 40960,
+			maxTokens: 40960,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-8b": {
+			id: "qwen/qwen3-8b",
+			name: "Qwen: Qwen3 8B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.028,
+				output: 0.1104,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 20000,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-14b": {
+			id: "qwen/qwen3-14b",
+			name: "Qwen: Qwen3 14B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.049999999999999996,
+				output: 0.22,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 40960,
+			maxTokens: 40960,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-32b": {
+			id: "qwen/qwen3-32b",
+			name: "Qwen: Qwen3 32B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.08,
+				output: 0.24,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 40960,
+			maxTokens: 40960,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-235b-a22b": {
+			id: "qwen/qwen3-235b-a22b",
+			name: "Qwen: Qwen3 235B A22B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.18,
+				output: 0.54,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 40960,
+			maxTokens: 40960,
+		} satisfies Model<"openai-completions">,
+		"openai/o4-mini-high": {
+			id: "openai/o4-mini-high",
+			name: "OpenAI: o4 Mini High",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.1,
+				output: 4.4,
+				cacheRead: 0.275,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-completions">,
+		"openai/o3": {
+			id: "openai/o3",
+			name: "OpenAI: o3",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 8,
+				cacheRead: 0.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-completions">,
+		"openai/o4-mini": {
+			id: "openai/o4-mini",
+			name: "OpenAI: o4 Mini",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.1,
+				output: 4.4,
+				cacheRead: 0.275,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4.1": {
+			id: "openai/gpt-4.1",
+			name: "OpenAI: GPT-4.1",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 8,
+				cacheRead: 0.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 1047576,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4.1-mini": {
+			id: "openai/gpt-4.1-mini",
+			name: "OpenAI: GPT-4.1 Mini",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 1.5999999999999999,
+				cacheRead: 0.09999999999999999,
+				cacheWrite: 0,
+			},
+			contextWindow: 1047576,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4.1-nano": {
+			id: "openai/gpt-4.1-nano",
+			name: "OpenAI: GPT-4.1 Nano",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.09999999999999999,
+				output: 0.39999999999999997,
+				cacheRead: 0.024999999999999998,
+				cacheWrite: 0,
+			},
+			contextWindow: 1047576,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"x-ai/grok-3-mini-beta": {
+			id: "x-ai/grok-3-mini-beta",
+			name: "xAI: Grok 3 Mini Beta",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 0.5,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"x-ai/grok-3-beta": {
+			id: "x-ai/grok-3-beta",
+			name: "xAI: Grok 3 Beta",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.75,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-4-maverick": {
+			id: "meta-llama/llama-4-maverick",
+			name: "Meta: Llama 4 Maverick",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.15,
+				output: 0.6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-4-scout": {
+			id: "meta-llama/llama-4-scout",
+			name: "Meta: Llama 4 Scout",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.08,
+				output: 0.3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 327680,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"deepseek/deepseek-chat-v3-0324": {
+			id: "deepseek/deepseek-chat-v3-0324",
+			name: "DeepSeek: DeepSeek V3 0324",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.19999999999999998,
+				output: 0.88,
+				cacheRead: 0.106,
+				cacheWrite: 0,
+			},
+			contextWindow: 163840,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-small-3.1-24b-instruct:free": {
+			id: "mistralai/mistral-small-3.1-24b-instruct:free",
+			name: "Mistral: Mistral Small 3.1 24B (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-small-3.1-24b-instruct": {
+			id: "mistralai/mistral-small-3.1-24b-instruct",
+			name: "Mistral: Mistral Small 3.1 24B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.03,
+				output: 0.11,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"google/gemma-3-27b-it:free": {
+			id: "google/gemma-3-27b-it:free",
+			name: "Google: Gemma 3 27B (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"google/gemma-3-27b-it": {
+			id: "google/gemma-3-27b-it",
+			name: "Google: Gemma 3 27B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.04,
+				output: 0.15,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 96000,
+			maxTokens: 96000,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwq-32b": {
+			id: "qwen/qwq-32b",
+			name: "Qwen: QwQ 32B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.15,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"google/gemini-2.0-flash-lite-001": {
+			id: "google/gemini-2.0-flash-lite-001",
+			name: "Google: Gemini 2.0 Flash Lite",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.075,
+				output: 0.3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"anthropic/claude-3.7-sonnet:thinking": {
+			id: "anthropic/claude-3.7-sonnet:thinking",
+			name: "Anthropic: Claude 3.7 Sonnet (thinking)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"anthropic/claude-3.7-sonnet": {
+			id: "anthropic/claude-3.7-sonnet",
+			name: "Anthropic: Claude 3.7 Sonnet",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-saba": {
+			id: "mistralai/mistral-saba",
+			name: "Mistral: Saba",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.19999999999999998,
+				output: 0.6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/o3-mini-high": {
+			id: "openai/o3-mini-high",
+			name: "OpenAI: o3 Mini High",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1.1,
+				output: 4.4,
+				cacheRead: 0.55,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-completions">,
+		"google/gemini-2.0-flash-001": {
+			id: "google/gemini-2.0-flash-001",
+			name: "Google: Gemini 2.0 Flash",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.09999999999999999,
+				output: 0.39999999999999997,
+				cacheRead: 0.024999999999999998,
+				cacheWrite: 0.18330000000000002,
+			},
+			contextWindow: 1048576,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen-vl-max": {
+			id: "qwen/qwen-vl-max",
+			name: "Qwen: Qwen VL Max",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.7999999999999999,
+				output: 3.1999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen-turbo": {
+			id: "qwen/qwen-turbo",
+			name: "Qwen: Qwen-Turbo",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.049999999999999996,
+				output: 0.19999999999999998,
+				cacheRead: 0.02,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen-plus": {
+			id: "qwen/qwen-plus",
+			name: "Qwen: Qwen-Plus",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 1.2,
+				cacheRead: 0.16,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen-max": {
+			id: "qwen/qwen-max",
+			name: "Qwen: Qwen-Max ",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1.5999999999999999,
+				output: 6.3999999999999995,
+				cacheRead: 0.64,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"openai/o3-mini": {
+			id: "openai/o3-mini",
+			name: "OpenAI: o3 Mini",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1.1,
+				output: 4.4,
+				cacheRead: 0.55,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-small-24b-instruct-2501": {
+			id: "mistralai/mistral-small-24b-instruct-2501",
+			name: "Mistral: Mistral Small 3",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.03,
+				output: 0.11,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"deepseek/deepseek-r1-distill-llama-70b": {
+			id: "deepseek/deepseek-r1-distill-llama-70b",
+			name: "DeepSeek: R1 Distill Llama 70B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.03,
+				output: 0.11,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"deepseek/deepseek-r1": {
+			id: "deepseek/deepseek-r1",
+			name: "DeepSeek: R1",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 163840,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"deepseek/deepseek-chat": {
+			id: "deepseek/deepseek-chat",
+			name: "DeepSeek: DeepSeek V3",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 163840,
+			maxTokens: 163840,
+		} satisfies Model<"openai-completions">,
+		"openai/o1": {
+			id: "openai/o1",
+			name: "OpenAI: o1",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 15,
+				output: 60,
+				cacheRead: 7.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-completions">,
+		"google/gemini-2.0-flash-exp:free": {
+			id: "google/gemini-2.0-flash-exp:free",
+			name: "Google: Gemini 2.0 Flash Experimental (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-3.3-70b-instruct:free": {
+			id: "meta-llama/llama-3.3-70b-instruct:free",
+			name: "Meta: Llama 3.3 70B Instruct (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-3.3-70b-instruct": {
+			id: "meta-llama/llama-3.3-70b-instruct",
+			name: "Meta: Llama 3.3 70B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.09999999999999999,
+				output: 0.32,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"amazon/nova-lite-v1": {
+			id: "amazon/nova-lite-v1",
+			name: "Amazon: Nova Lite 1.0",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.06,
+				output: 0.24,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 300000,
+			maxTokens: 5120,
+		} satisfies Model<"openai-completions">,
+		"amazon/nova-micro-v1": {
+			id: "amazon/nova-micro-v1",
+			name: "Amazon: Nova Micro 1.0",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.035,
+				output: 0.14,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 5120,
+		} satisfies Model<"openai-completions">,
+		"amazon/nova-pro-v1": {
+			id: "amazon/nova-pro-v1",
+			name: "Amazon: Nova Pro 1.0",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.7999999999999999,
+				output: 3.1999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 300000,
+			maxTokens: 5120,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4o-2024-11-20": {
+			id: "openai/gpt-4o-2024-11-20",
+			name: "OpenAI: GPT-4o (2024-11-20)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2.5,
+				output: 10,
+				cacheRead: 1.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-large-2411": {
+			id: "mistralai/mistral-large-2411",
+			name: "Mistral Large 2411",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-large-2407": {
+			id: "mistralai/mistral-large-2407",
+			name: "Mistral Large 2407",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/pixtral-large-2411": {
+			id: "mistralai/pixtral-large-2411",
+			name: "Mistral: Pixtral Large 2411",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"thedrummer/unslopnemo-12b": {
+			id: "thedrummer/unslopnemo-12b",
+			name: "TheDrummer: UnslopNemo 12B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"anthropic/claude-3.5-haiku-20241022": {
+			id: "anthropic/claude-3.5-haiku-20241022",
+			name: "Anthropic: Claude 3.5 Haiku (2024-10-22)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.7999999999999999,
+				output: 4,
+				cacheRead: 0.08,
+				cacheWrite: 1,
+			},
+			contextWindow: 200000,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"anthropic/claude-3.5-haiku": {
+			id: "anthropic/claude-3.5-haiku",
+			name: "Anthropic: Claude 3.5 Haiku",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.7999999999999999,
+				output: 4,
+				cacheRead: 0.08,
+				cacheWrite: 1,
+			},
+			contextWindow: 200000,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"anthropic/claude-3.5-sonnet": {
+			id: "anthropic/claude-3.5-sonnet",
+			name: "Anthropic: Claude 3.5 Sonnet",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 6,
+				output: 30,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"mistralai/ministral-8b": {
+			id: "mistralai/ministral-8b",
+			name: "Mistral: Ministral 8B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.09999999999999999,
+				output: 0.09999999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/ministral-3b": {
+			id: "mistralai/ministral-3b",
+			name: "Mistral: Ministral 3B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.04,
+				output: 0.04,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"nvidia/llama-3.1-nemotron-70b-instruct": {
+			id: "nvidia/llama-3.1-nemotron-70b-instruct",
+			name: "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1.2,
+				output: 1.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"thedrummer/rocinante-12b": {
+			id: "thedrummer/rocinante-12b",
+			name: "TheDrummer: Rocinante 12B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.16999999999999998,
+				output: 0.43,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-3.2-3b-instruct": {
+			id: "meta-llama/llama-3.2-3b-instruct",
+			name: "Meta: Llama 3.2 3B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.02,
+				output: 0.02,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"qwen/qwen-2.5-72b-instruct": {
+			id: "qwen/qwen-2.5-72b-instruct",
+			name: "Qwen2.5 72B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.12,
+				output: 0.39,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"mistralai/pixtral-12b": {
+			id: "mistralai/pixtral-12b",
+			name: "Mistral: Pixtral 12B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.09999999999999999,
+				output: 0.09999999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"cohere/command-r-08-2024": {
+			id: "cohere/command-r-08-2024",
+			name: "Cohere: Command R (08-2024)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.15,
+				output: 0.6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4000,
+		} satisfies Model<"openai-completions">,
+		"cohere/command-r-plus-08-2024": {
+			id: "cohere/command-r-plus-08-2024",
+			name: "Cohere: Command R+ (08-2024)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2.5,
+				output: 10,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4000,
+		} satisfies Model<"openai-completions">,
+		"sao10k/l3.1-euryale-70b": {
+			id: "sao10k/l3.1-euryale-70b",
+			name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.65,
+				output: 0.75,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"microsoft/phi-3.5-mini-128k-instruct": {
+			id: "microsoft/phi-3.5-mini-128k-instruct",
+			name: "Microsoft: Phi-3.5 Mini 128K Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.09999999999999999,
+				output: 0.09999999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4o-2024-08-06": {
+			id: "openai/gpt-4o-2024-08-06",
+			name: "OpenAI: GPT-4o (2024-08-06)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2.5,
+				output: 10,
+				cacheRead: 1.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-3.1-8b-instruct": {
+			id: "meta-llama/llama-3.1-8b-instruct",
+			name: "Meta: Llama 3.1 8B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.02,
+				output: 0.03,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-3.1-405b-instruct": {
+			id: "meta-llama/llama-3.1-405b-instruct",
+			name: "Meta: Llama 3.1 405B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 3.5,
+				output: 3.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 10000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-3.1-70b-instruct": {
+			id: "meta-llama/llama-3.1-70b-instruct",
+			name: "Meta: Llama 3.1 70B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.39999999999999997,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-nemo": {
+			id: "mistralai/mistral-nemo",
+			name: "Mistral: Mistral Nemo",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.02,
+				output: 0.04,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4o-mini-2024-07-18": {
+			id: "openai/gpt-4o-mini-2024-07-18",
+			name: "OpenAI: GPT-4o-mini (2024-07-18)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.15,
+				output: 0.6,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4o-mini": {
+			id: "openai/gpt-4o-mini",
+			name: "OpenAI: GPT-4o-mini",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.15,
+				output: 0.6,
+				cacheRead: 0.075,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"sao10k/l3-euryale-70b": {
+			id: "sao10k/l3-euryale-70b",
+			name: "Sao10k: Llama 3 Euryale 70B v2.1",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1.48,
+				output: 1.48,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
+			maxTokens: 8192,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-7b-instruct:free": {
+			id: "mistralai/mistral-7b-instruct:free",
+			name: "Mistral: Mistral 7B Instruct (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-7b-instruct": {
+			id: "mistralai/mistral-7b-instruct",
+			name: "Mistral: Mistral 7B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.028,
+				output: 0.054,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"microsoft/phi-3-mini-128k-instruct": {
+			id: "microsoft/phi-3-mini-128k-instruct",
+			name: "Microsoft: Phi-3 Mini 128K Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.09999999999999999,
+				output: 0.09999999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"microsoft/phi-3-medium-128k-instruct": {
+			id: "microsoft/phi-3-medium-128k-instruct",
+			name: "Microsoft: Phi-3 Medium 128K Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 1,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4o-2024-05-13": {
+			id: "openai/gpt-4o-2024-05-13",
+			name: "OpenAI: GPT-4o (2024-05-13)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 5,
+				output: 15,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4o": {
+			id: "openai/gpt-4o",
+			name: "OpenAI: GPT-4o",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2.5,
+				output: 10,
+				cacheRead: 1.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4o:extended": {
+			id: "openai/gpt-4o:extended",
+			name: "OpenAI: GPT-4o (extended)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 6,
+				output: 18,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-3-70b-instruct": {
+			id: "meta-llama/llama-3-70b-instruct",
+			name: "Meta: Llama 3 70B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/llama-3-8b-instruct": {
+			id: "meta-llama/llama-3-8b-instruct",
+			name: "Meta: Llama 3 8B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.03,
+				output: 0.06,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mixtral-8x22b-instruct": {
+			id: "mistralai/mixtral-8x22b-instruct",
+			name: "Mistral: Mixtral 8x22B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 65536,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4-turbo": {
+			id: "openai/gpt-4-turbo",
+			name: "OpenAI: GPT-4 Turbo",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 10,
+				output: 30,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"anthropic/claude-3-haiku": {
+			id: "anthropic/claude-3-haiku",
+			name: "Anthropic: Claude 3 Haiku",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 1.25,
+				cacheRead: 0.03,
+				cacheWrite: 0.3,
+			},
+			contextWindow: 200000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"anthropic/claude-3-opus": {
+			id: "anthropic/claude-3-opus",
+			name: "Anthropic: Claude 3 Opus",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 15,
+				output: 75,
+				cacheRead: 1.5,
+				cacheWrite: 18.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-large": {
+			id: "mistralai/mistral-large",
+			name: "Mistral Large",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 2,
+				output: 6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-3.5-turbo-0613": {
+			id: "openai/gpt-3.5-turbo-0613",
+			name: "OpenAI: GPT-3.5 Turbo (older v0613)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 4095,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4-turbo-preview": {
+			id: "openai/gpt-4-turbo-preview",
+			name: "OpenAI: GPT-4 Turbo Preview",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 10,
+				output: 30,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-tiny": {
+			id: "mistralai/mistral-tiny",
+			name: "Mistral Tiny",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.25,
+				output: 0.25,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"mistralai/mixtral-8x7b-instruct": {
+			id: "mistralai/mixtral-8x7b-instruct",
+			name: "Mistral: Mixtral 8x7B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.54,
+				output: 0.54,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4-1106-preview": {
+			id: "openai/gpt-4-1106-preview",
+			name: "OpenAI: GPT-4 Turbo (older v1106)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 10,
+				output: 30,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-3.5-turbo-16k": {
+			id: "openai/gpt-3.5-turbo-16k",
+			name: "OpenAI: GPT-3.5 Turbo 16k",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 3,
+				output: 4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 16385,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4-0314": {
+			id: "openai/gpt-4-0314",
+			name: "OpenAI: GPT-4 (older v0314)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 30,
+				output: 60,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 8191,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4": {
+			id: "openai/gpt-4",
+			name: "OpenAI: GPT-4",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 30,
+				output: 60,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 8191,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-3.5-turbo": {
+			id: "openai/gpt-3.5-turbo",
+			name: "OpenAI: GPT-3.5 Turbo",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.5,
+				output: 1.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 16385,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openrouter/auto": {
+			id: "openrouter/auto",
+			name: "OpenRouter: Auto Router",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 2000000,
+			maxTokens: 30000,
+		} satisfies Model<"openai-completions">,
+	},
+	"google-gemini-cli": {
+		"gemini-2.5-pro": {
+			id: "gemini-2.5-pro",
+			name: "Gemini 2.5 Pro (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: "https://cloudcode-pa.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"google-gemini-cli">,
+		"gemini-2.5-flash": {
+			id: "gemini-2.5-flash",
+			name: "Gemini 2.5 Flash (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: "https://cloudcode-pa.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"google-gemini-cli">,
+		"gemini-2.0-flash": {
+			id: "gemini-2.0-flash",
+			name: "Gemini 2.0 Flash (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: "https://cloudcode-pa.googleapis.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 8192,
+		} satisfies Model<"google-gemini-cli">,
+		"gemini-3-pro-preview": {
+			id: "gemini-3-pro-preview",
+			name: "Gemini 3 Pro Preview (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: "https://cloudcode-pa.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"google-gemini-cli">,
+		"gemini-3-flash-preview": {
+			id: "gemini-3-flash-preview",
+			name: "Gemini 3 Flash Preview (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: "https://cloudcode-pa.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"google-gemini-cli">,
+	},
+	"google-antigravity": {
+		"gemini-3-pro-high": {
+			id: "gemini-3-pro-high",
+			name: "Gemini 3 Pro High (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"google-gemini-cli">,
+		"gemini-3-pro-low": {
+			id: "gemini-3-pro-low",
+			name: "Gemini 3 Pro Low (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"google-gemini-cli">,
+		"gemini-3-flash": {
+			id: "gemini-3-flash",
+			name: "Gemini 3 Flash (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"google-gemini-cli">,
+		"claude-sonnet-4-5": {
+			id: "claude-sonnet-4-5",
+			name: "Claude Sonnet 4.5 (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"google-gemini-cli">,
+		"claude-sonnet-4-5-thinking": {
+			id: "claude-sonnet-4-5-thinking",
+			name: "Claude Sonnet 4.5 Thinking (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"google-gemini-cli">,
+		"claude-opus-4-5-thinking": {
+			id: "claude-opus-4-5-thinking",
+			name: "Claude Opus 4.5 Thinking (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"google-gemini-cli">,
+		"gpt-oss-120b-medium": {
+			id: "gpt-oss-120b-medium",
+			name: "GPT-OSS 120B Medium (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 32768,
+		} satisfies Model<"google-gemini-cli">,
 	},
 } as const;
diff --git a/packages/coding-agent/docs/session-tree-plan.md b/packages/coding-agent/docs/session-tree-plan.md
new file mode 100644
index 00000000..5f2371df
--- /dev/null
+++ b/packages/coding-agent/docs/session-tree-plan.md
@@ -0,0 +1,86 @@
+# Session Tree Implementation Plan
+
+Reference: [session-tree.md](./session-tree.md)
+
+## Phase 1: SessionManager Core
+
+- [x] Update entry types with `id`, `parentId` fields (using TreeNode intersection)
+- [x] Add `version` field to `SessionHeader`
+- [x] Change `CompactionEntry.firstKeptEntryIndex` → `firstKeptEntryId`
+- [x] Add `BranchSummaryEntry` type
+- [x] Add `byId: Map<string, ConversationEntry>` index
+- [x] Add `leafId: string` tracking
+- [x] Implement `getPath(fromId?)` tree traversal
+- [x] Implement `getEntry(id)` lookup
+- [x] Implement `getLeafId()` helper
+- [x] Update `_buildIndex()` to populate `byId` map
+- [x] Update `saveMessage()` to include id/parentId (returns id)
+- [x] Update `saveCompaction()` signature and fields (returns id)
+- [x] Update `saveThinkingLevelChange()` to include id/parentId (returns id)
+- [x] Update `saveModelChange()` to include id/parentId (returns id)
+- [x] Update `buildSessionContext()` to use `getPath()` traversal
+
+### Type Hierarchy
+
+```typescript
+// Tree fields (added by SessionManager)
+interface TreeNode { id, parentId, timestamp }
+
+// Content types (for input)
+interface MessageContent { type: "message"; message: AppMessage }
+interface CompactionContent { type: "compaction"; summary; firstKeptEntryId; tokensBefore }
+// etc...
+
+// Full entry types (TreeNode & Content)
+type SessionMessageEntry = TreeNode & MessageContent;
+type CompactionEntry = TreeNode & CompactionContent;
+// etc...
+```
+
+## Phase 2: Migration
+
+- [x] Add `CURRENT_SESSION_VERSION = 2` constant
+- [x] Implement `_migrateToV2()` for v1→v2
+- [x] Update `setSessionFile()` to detect version and migrate
+- [x] Implement `_rewriteFile()` for post-migration persistence
+- [x] Handle `firstKeptEntryIndex` → `firstKeptEntryId` conversion in migration
+
+## Phase 3: Branching
+
+- [x] Implement `branchInPlace(id)` - switch leaf pointer
+- [x] Implement `branchWithSummary(id, summary)` - create summary entry
+- [x] Update `branchToNewFile()` to use IDs (no remapping)
+- [ ] Update `AgentSession.branch()` to use new API
+
+## Phase 4: Compaction Integration
+
+- [x] Update `compaction.ts` to work with IDs
+- [x] Update `prepareCompaction()` to return `firstKeptEntryId`
+- [x] Update `compact()` to return `CompactionResult` with `firstKeptEntryId`
+- [x] Update `AgentSession` compaction methods
+- [x] Add `firstKeptEntryId` to `before_compact` hook event
+
+## Phase 5: Testing
+
+- [ ] Add test fixtures from existing sessions
+- [ ] Test migration of v1 sessions
+- [ ] Test context building with tree structure
+- [ ] Test branching operations
+- [ ] Test compaction with IDs
+- [x] Update existing tests for new types
+
+## Phase 6: UI Integration
+
+- [ ] Update `/branch` command for new API
+- [ ] Add `/branch-here` command for in-place branching
+- [ ] Add `/branches` command to list branches (future)
+- [ ] Update session display to show tree info (future)
+
+## Notes
+
+- All save methods return the new entry's ID
+- Migration rewrites file on first load if version < CURRENT_VERSION
+- Existing sessions become linear chains after migration (parentId = previous entry)
+- Tree features available immediately after migration
+- SessionHeader does NOT have id/parentId (it's metadata, not part of tree)
+- Content types allow clean input/output separation
diff --git a/packages/coding-agent/examples/hooks/custom-compaction.ts b/packages/coding-agent/examples/hooks/custom-compaction.ts
index 3967b1ce..1781e7e3 100644
--- a/packages/coding-agent/examples/hooks/custom-compaction.ts
+++ b/packages/coding-agent/examples/hooks/custom-compaction.ts
@@ -94,14 +94,12 @@ Format the summary as structured markdown with clear sections.`,
 				return;
 			}
 
-			// Return a compaction entry that discards ALL messages
-			// firstKeptEntryIndex points past all current entries
+			// Return compaction content - SessionManager adds id/parentId
+			// Use firstKeptEntryId from event to keep recent messages
 			return {
-				compactionEntry: {
-					type: "compaction" as const,
-					timestamp: new Date().toISOString(),
+				compaction: {
 					summary,
-					firstKeptEntryIndex: entries.length,
+					firstKeptEntryId: event.firstKeptEntryId,
 					tokensBefore,
 				},
 			};
diff --git a/packages/coding-agent/src/core/agent-session.ts b/packages/coding-agent/src/core/agent-session.ts
index 16f33e27..fe4804a1 100644
--- a/packages/coding-agent/src/core/agent-session.ts
+++ b/packages/coding-agent/src/core/agent-session.ts
@@ -754,7 +754,12 @@ export class AgentSession {
 
 			const preparation = prepareCompaction(entries, settings);
 			if (!preparation) {
-				throw new Error("Already compacted");
+				// Check why we can't compact
+				const lastEntry = entries[entries.length - 1];
+				if (lastEntry?.type === "compaction") {
+					throw new Error("Already compacted");
+				}
+				throw new Error("Nothing to compact (session too small or needs migration)");
 			}
 
 			// Find previous compaction summary if any
@@ -766,7 +771,7 @@ export class AgentSession {
 				}
 			}
 
-			let compactionEntry: CompactionEntry | undefined;
+			let hookCompaction: { summary: string; firstKeptEntryId: string; tokensBefore: number } | undefined;
 			let fromHook = false;
 
 			if (this._hookRunner?.hasHandlers("session")) {
@@ -777,6 +782,7 @@ export class AgentSession {
 					previousSessionFile: null,
 					reason: "before_compact",
 					cutPoint: preparation.cutPoint,
+					firstKeptEntryId: preparation.firstKeptEntryId,
 					previousSummary,
 					messagesToSummarize: [...preparation.messagesToSummarize],
 					messagesToKeep: [...preparation.messagesToKeep],
@@ -791,14 +797,24 @@ export class AgentSession {
 					throw new Error("Compaction cancelled");
 				}
 
-				if (result?.compactionEntry) {
-					compactionEntry = result.compactionEntry;
+				if (result?.compaction) {
+					hookCompaction = result.compaction;
 					fromHook = true;
 				}
 			}
 
-			if (!compactionEntry) {
-				compactionEntry = await compact(
+			let summary: string;
+			let firstKeptEntryId: string;
+			let tokensBefore: number;
+
+			if (hookCompaction) {
+				// Hook provided compaction content
+				summary = hookCompaction.summary;
+				firstKeptEntryId = hookCompaction.firstKeptEntryId;
+				tokensBefore = hookCompaction.tokensBefore;
+			} else {
+				// Generate compaction result
+				const result = await compact(
 					entries,
 					this.model,
 					settings,
@@ -806,33 +822,41 @@ export class AgentSession {
 					this._compactionAbortController.signal,
 					customInstructions,
 				);
+				summary = result.summary;
+				firstKeptEntryId = result.firstKeptEntryId;
+				tokensBefore = result.tokensBefore;
 			}
 
 			if (this._compactionAbortController.signal.aborted) {
 				throw new Error("Compaction cancelled");
 			}
 
-			this.sessionManager.saveCompaction(compactionEntry);
+			this.sessionManager.saveCompaction(summary, firstKeptEntryId, tokensBefore);
 			const newEntries = this.sessionManager.getEntries();
 			const sessionContext = this.sessionManager.buildSessionContext();
 			this.agent.replaceMessages(sessionContext.messages);
 
-			if (this._hookRunner) {
+			// Get the saved compaction entry for the hook
+			const savedCompactionEntry = newEntries.find((e) => e.type === "compaction" && e.summary === summary) as
+				| CompactionEntry
+				| undefined;
+
+			if (this._hookRunner && savedCompactionEntry) {
 				await this._hookRunner.emit({
 					type: "session",
 					entries: newEntries,
 					sessionFile: this.sessionFile,
 					previousSessionFile: null,
 					reason: "compact",
-					compactionEntry,
-					tokensBefore: compactionEntry.tokensBefore,
+					compactionEntry: savedCompactionEntry,
+					tokensBefore,
 					fromHook,
 				});
 			}
 
 			return {
-				tokensBefore: compactionEntry.tokensBefore,
-				summary: compactionEntry.summary,
+				tokensBefore,
+				summary,
 			};
 		} finally {
 			this._compactionAbortController = null;
@@ -928,7 +952,7 @@ export class AgentSession {
 				}
 			}
 
-			let compactionEntry: CompactionEntry | undefined;
+			let hookCompaction: { summary: string; firstKeptEntryId: string; tokensBefore: number } | undefined;
 			let fromHook = false;
 
 			if (this._hookRunner?.hasHandlers("session")) {
@@ -939,6 +963,7 @@ export class AgentSession {
 					previousSessionFile: null,
 					reason: "before_compact",
 					cutPoint: preparation.cutPoint,
+					firstKeptEntryId: preparation.firstKeptEntryId,
 					previousSummary,
 					messagesToSummarize: [...preparation.messagesToSummarize],
 					messagesToKeep: [...preparation.messagesToKeep],
@@ -954,20 +979,33 @@ export class AgentSession {
 					return;
 				}
 
-				if (hookResult?.compactionEntry) {
-					compactionEntry = hookResult.compactionEntry;
+				if (hookResult?.compaction) {
+					hookCompaction = hookResult.compaction;
 					fromHook = true;
 				}
 			}
 
-			if (!compactionEntry) {
-				compactionEntry = await compact(
+			let summary: string;
+			let firstKeptEntryId: string;
+			let tokensBefore: number;
+
+			if (hookCompaction) {
+				// Hook provided compaction content
+				summary = hookCompaction.summary;
+				firstKeptEntryId = hookCompaction.firstKeptEntryId;
+				tokensBefore = hookCompaction.tokensBefore;
+			} else {
+				// Generate compaction result
+				const compactResult = await compact(
 					entries,
 					this.model,
 					settings,
 					apiKey,
 					this._autoCompactionAbortController.signal,
 				);
+				summary = compactResult.summary;
+				firstKeptEntryId = compactResult.firstKeptEntryId;
+				tokensBefore = compactResult.tokensBefore;
 			}
 
 			if (this._autoCompactionAbortController.signal.aborted) {
@@ -975,27 +1013,32 @@ export class AgentSession {
 				return;
 			}
 
-			this.sessionManager.saveCompaction(compactionEntry);
+			this.sessionManager.saveCompaction(summary, firstKeptEntryId, tokensBefore);
 			const newEntries = this.sessionManager.getEntries();
 			const sessionContext = this.sessionManager.buildSessionContext();
 			this.agent.replaceMessages(sessionContext.messages);
 
-			if (this._hookRunner) {
+			// Get the saved compaction entry for the hook
+			const savedCompactionEntry = newEntries.find((e) => e.type === "compaction" && e.summary === summary) as
+				| CompactionEntry
+				| undefined;
+
+			if (this._hookRunner && savedCompactionEntry) {
 				await this._hookRunner.emit({
 					type: "session",
 					entries: newEntries,
 					sessionFile: this.sessionFile,
 					previousSessionFile: null,
 					reason: "compact",
-					compactionEntry,
-					tokensBefore: compactionEntry.tokensBefore,
+					compactionEntry: savedCompactionEntry,
+					tokensBefore,
 					fromHook,
 				});
 			}
 
 			const result: CompactionResult = {
-				tokensBefore: compactionEntry.tokensBefore,
-				summary: compactionEntry.summary,
+				tokensBefore,
+				summary,
 			};
 			this._emit({ type: "auto_compaction_end", result, aborted: false, willRetry });
 
diff --git a/packages/coding-agent/src/core/compaction.ts b/packages/coding-agent/src/core/compaction.ts
index af4edfb8..8abfef74 100644
--- a/packages/coding-agent/src/core/compaction.ts
+++ b/packages/coding-agent/src/core/compaction.ts
@@ -9,7 +9,14 @@ import type { AppMessage } from "@mariozechner/pi-agent-core";
 import type { AssistantMessage, Model, Usage } from "@mariozechner/pi-ai";
 import { complete } from "@mariozechner/pi-ai";
 import { messageTransformer } from "./messages.js";
-import type { CompactionEntry, SessionEntry } from "./session-manager.js";
+import type { CompactionEntry, ConversationEntry, SessionEntry } from "./session-manager.js";
+
+/** Result from compact() - SessionManager adds uuid/parentUuid when saving */
+export interface CompactionResult {
+	summary: string;
+	firstKeptEntryId: string;
+	tokensBefore: number;
+}
 
 // ============================================================================
 // Types
@@ -327,6 +334,8 @@ export async function generateSummary(
 
 export interface CompactionPreparation {
 	cutPoint: CutPointResult;
+	/** UUID of first entry to keep */
+	firstKeptEntryId: string;
 	/** Messages that will be summarized and discarded */
 	messagesToSummarize: AppMessage[];
 	/** Messages that will be kept after the summary (recent turns) */
@@ -355,6 +364,16 @@ export function prepareCompaction(entries: SessionEntry[], settings: CompactionS
 
 	const cutPoint = findCutPoint(entries, boundaryStart, boundaryEnd, settings.keepRecentTokens);
 
+	// Get UUID of first kept entry
+	const firstKeptEntry = entries[cutPoint.firstKeptEntryIndex];
+	if (firstKeptEntry.type === "session") {
+		return null; // Can't compact if first kept is header
+	}
+	const firstKeptEntryId = (firstKeptEntry as ConversationEntry).id;
+	if (!firstKeptEntryId) {
+		return null; // Session needs migration
+	}
+
 	const historyEnd = cutPoint.isSplitTurn ? cutPoint.turnStartIndex : cutPoint.firstKeptEntryIndex;
 
 	// Messages to summarize (will be discarded after summary)
@@ -375,7 +394,7 @@ export function prepareCompaction(entries: SessionEntry[], settings: CompactionS
 		}
 	}
 
-	return { cutPoint, messagesToSummarize, messagesToKeep, tokensBefore, boundaryStart };
+	return { cutPoint, firstKeptEntryId, messagesToSummarize, messagesToKeep, tokensBefore, boundaryStart };
 }
 
 // ============================================================================
@@ -394,9 +413,9 @@ Be concise. Focus on information needed to understand the retained recent work.`
 
 /**
  * Calculate compaction and generate summary.
- * Returns the CompactionEntry to append to the session file.
+ * Returns CompactionResult - SessionManager adds uuid/parentUuid when saving.
  *
- * @param entries - All session entries
+ * @param entries - All session entries (must have uuid fields for v2)
  * @param model - Model to use for summarization
  * @param settings - Compaction settings
  * @param apiKey - API key for LLM
@@ -410,7 +429,7 @@ export async function compact(
 	apiKey: string,
 	signal?: AbortSignal,
 	customInstructions?: string,
-): Promise<CompactionEntry> {
+): Promise<CompactionResult> {
 	// Don't compact if the last entry is already a compaction
 	if (entries.length > 0 && entries[entries.length - 1].type === "compaction") {
 		throw new Error("Already compacted");
@@ -490,11 +509,19 @@ export async function compact(
 		);
 	}
 
+	// Get UUID of first kept entry
+	const firstKeptEntry = entries[cutResult.firstKeptEntryIndex];
+	if (firstKeptEntry.type === "session") {
+		throw new Error("Cannot compact: first kept entry is session header");
+	}
+	const firstKeptEntryId = (firstKeptEntry as ConversationEntry).id;
+	if (!firstKeptEntryId) {
+		throw new Error("First kept entry has no UUID - session may need migration");
+	}
+
 	return {
-		type: "compaction",
-		timestamp: new Date().toISOString(),
 		summary,
-		firstKeptEntryIndex: cutResult.firstKeptEntryIndex,
+		firstKeptEntryId,
 		tokensBefore,
 	};
 }
diff --git a/packages/coding-agent/src/core/hooks/types.ts b/packages/coding-agent/src/core/hooks/types.ts
index a60d009b..a51a93bf 100644
--- a/packages/coding-agent/src/core/hooks/types.ts
+++ b/packages/coding-agent/src/core/hooks/types.ts
@@ -130,6 +130,8 @@ export type SessionEvent =
 	| (SessionEventBase & {
 			reason: "before_compact";
 			cutPoint: CutPointResult;
+			/** ID of first entry to keep (for hooks that return CompactionEntry) */
+			firstKeptEntryId: string;
 			/** Summary from previous compaction, if any. Include this in your summary to preserve context. */
 			previousSummary?: string;
 			/** Messages that will be summarized and discarded */
@@ -351,8 +353,12 @@ export interface SessionEventResult {
 	cancel?: boolean;
 	/** If true (for before_branch only), skip restoring conversation to branch point while still creating the branched session file */
 	skipConversationRestore?: boolean;
-	/** Custom compaction entry (for before_compact event) */
-	compactionEntry?: CompactionEntry;
+	/** Custom compaction result (for before_compact event) - SessionManager adds id/parentId */
+	compaction?: {
+		summary: string;
+		firstKeptEntryId: string;
+		tokensBefore: number;
+	};
 }
 
 // ============================================================================
diff --git a/packages/coding-agent/src/core/session-manager.ts b/packages/coding-agent/src/core/session-manager.ts
index dd118afd..3b9eda0b 100644
--- a/packages/coding-agent/src/core/session-manager.ts
+++ b/packages/coding-agent/src/core/session-manager.ts
@@ -1,9 +1,11 @@
 import type { AppMessage } from "@mariozechner/pi-agent-core";
 import { randomBytes } from "crypto";
-import { appendFileSync, existsSync, mkdirSync, readdirSync, readFileSync, statSync } from "fs";
+import { appendFileSync, existsSync, mkdirSync, readdirSync, readFileSync, statSync, writeFileSync } from "fs";
 import { join, resolve } from "path";
 import { getAgentDir as getDefaultAgentDir } from "../config.js";
 
+export const CURRENT_SESSION_VERSION = 2;
+
 function uuidv4(): string {
 	const bytes = randomBytes(16);
 	bytes[6] = (bytes[6] & 0x0f) | 0x40;
@@ -12,47 +14,89 @@ function uuidv4(): string {
 	return `${hex.slice(0, 8)}-${hex.slice(8, 12)}-${hex.slice(12, 16)}-${hex.slice(16, 20)}-${hex.slice(20, 32)}`;
 }
 
+// ============================================================================
+// Session Header (metadata, not part of conversation tree)
+// ============================================================================
+
 export interface SessionHeader {
 	type: "session";
+	version?: number; // v1 sessions don't have this
 	id: string;
 	timestamp: string;
 	cwd: string;
 	branchedFrom?: string;
 }
 
-export interface SessionMessageEntry {
-	type: "message";
+// ============================================================================
+// Tree Node (added by SessionManager to all conversation entries)
+// ============================================================================
+
+export interface TreeNode {
+	id: string;
+	parentId: string | null;
 	timestamp: string;
+}
+
+// ============================================================================
+// Content Types (what distinguishes entries - used for input)
+// ============================================================================
+
+export interface MessageContent {
+	type: "message";
 	message: AppMessage;
 }
 
-export interface ThinkingLevelChangeEntry {
+export interface ThinkingLevelContent {
 	type: "thinking_level_change";
-	timestamp: string;
 	thinkingLevel: string;
 }
 
-export interface ModelChangeEntry {
+export interface ModelChangeContent {
 	type: "model_change";
-	timestamp: string;
 	provider: string;
 	modelId: string;
 }
 
-export interface CompactionEntry {
+export interface CompactionContent {
 	type: "compaction";
-	timestamp: string;
 	summary: string;
-	firstKeptEntryIndex: number;
+	firstKeptEntryId: string;
 	tokensBefore: number;
 }
 
-export type SessionEntry =
-	| SessionHeader
+export interface BranchSummaryContent {
+	type: "branch_summary";
+	summary: string;
+}
+
+/** Union of all content types (for input) */
+export type ConversationContent =
+	| MessageContent
+	| ThinkingLevelContent
+	| ModelChangeContent
+	| CompactionContent
+	| BranchSummaryContent;
+
+// ============================================================================
+// Full Entry Types (TreeNode + Content - returned from SessionManager)
+// ============================================================================
+
+export type SessionMessageEntry = TreeNode & MessageContent;
+export type ThinkingLevelChangeEntry = TreeNode & ThinkingLevelContent;
+export type ModelChangeEntry = TreeNode & ModelChangeContent;
+export type CompactionEntry = TreeNode & CompactionContent;
+export type BranchSummaryEntry = TreeNode & BranchSummaryContent;
+
+/** Conversation entry - has id/parentId for tree structure */
+export type ConversationEntry =
 	| SessionMessageEntry
 	| ThinkingLevelChangeEntry
 	| ModelChangeEntry
-	| CompactionEntry;
+	| CompactionEntry
+	| BranchSummaryEntry;
+
+/** Any session entry (header or conversation) */
+export type SessionEntry = SessionHeader | ConversationEntry;
 
 export interface SessionContext {
 	messages: AppMessage[];
@@ -87,6 +131,45 @@ export function createSummaryMessage(summary: string): AppMessage {
 	};
 }
 
+/**
+ * Migrate v1 entries to v2 format by adding id/parentId fields.
+ * Mutates entries in place. Safe to call on already-migrated entries.
+ */
+export function migrateSessionEntries(entries: SessionEntry[]): void {
+	// Check if already migrated
+	const firstConv = entries.find((e) => e.type !== "session");
+	if (firstConv && "id" in firstConv && firstConv.id) {
+		return; // Already migrated
+	}
+
+	let prevId: string | null = null;
+	for (const entry of entries) {
+		if (entry.type === "session") {
+			entry.version = CURRENT_SESSION_VERSION;
+			continue;
+		}
+
+		// Add id/parentId to conversation entries
+		const convEntry = entry as ConversationEntry;
+		convEntry.id = uuidv4();
+		convEntry.parentId = prevId;
+		prevId = convEntry.id;
+
+		// Convert firstKeptEntryIndex to firstKeptEntryId for compaction
+		if (entry.type === "compaction") {
+			const comp = entry as CompactionEntry & { firstKeptEntryIndex?: number };
+			if (typeof comp.firstKeptEntryIndex === "number") {
+				// Find the entry at that index and get its id
+				const targetEntry = entries[comp.firstKeptEntryIndex];
+				if (targetEntry && targetEntry.type !== "session") {
+					comp.firstKeptEntryId = (targetEntry as ConversationEntry).id;
+				}
+				delete comp.firstKeptEntryIndex;
+			}
+		}
+	}
+}
+
 /** Exported for compaction.test.ts */
 export function parseSessionEntries(content: string): SessionEntry[] {
 	const entries: SessionEntry[] = [];
@@ -115,59 +198,108 @@ export function getLatestCompactionEntry(entries: SessionEntry[]): CompactionEnt
 }
 
 /**
- * Build the session context from entries. This is what gets sent to the LLM.
- *
- * If there's a compaction entry, returns the summary message plus messages
- * from `firstKeptEntryIndex` onwards. Otherwise returns all messages.
- *
- * Also extracts the current thinking level and model from the entries.
+ * Build the session context from entries using tree traversal.
+ * If leafId is provided, walks from that entry to root.
+ * Handles compaction and branch summaries along the path.
  */
-export function buildSessionContext(entries: SessionEntry[]): SessionContext {
+export function buildSessionContext(entries: SessionEntry[], leafId?: string): SessionContext {
+	// Build uuid index for conversation entries
+	const byId = new Map<string, ConversationEntry>();
+	for (const entry of entries) {
+		if (entry.type !== "session") {
+			byId.set(entry.id, entry);
+		}
+	}
+
+	// Find leaf
+	let leaf: ConversationEntry | undefined;
+	if (leafId) {
+		leaf = byId.get(leafId);
+	} else {
+		// Find last conversation entry
+		for (let i = entries.length - 1; i >= 0; i--) {
+			if (entries[i].type !== "session") {
+				leaf = entries[i] as ConversationEntry;
+				break;
+			}
+		}
+	}
+
+	if (!leaf) {
+		return { messages: [], thinkingLevel: "off", model: null };
+	}
+
+	// Walk from leaf to root, collecting path
+	const path: ConversationEntry[] = [];
+	let current: ConversationEntry | undefined = leaf;
+	while (current) {
+		path.unshift(current);
+		current = current.parentId ? byId.get(current.parentId) : undefined;
+	}
+
+	// Extract settings and find compaction
 	let thinkingLevel = "off";
 	let model: { provider: string; modelId: string } | null = null;
+	let compaction: CompactionEntry | null = null;
 
-	for (const entry of entries) {
+	for (const entry of path) {
 		if (entry.type === "thinking_level_change") {
 			thinkingLevel = entry.thinkingLevel;
 		} else if (entry.type === "model_change") {
 			model = { provider: entry.provider, modelId: entry.modelId };
 		} else if (entry.type === "message" && entry.message.role === "assistant") {
 			model = { provider: entry.message.provider, modelId: entry.message.model };
+		} else if (entry.type === "compaction") {
+			compaction = entry;
 		}
 	}
 
-	let latestCompactionIndex = -1;
-	for (let i = entries.length - 1; i >= 0; i--) {
-		if (entries[i].type === "compaction") {
-			latestCompactionIndex = i;
-			break;
-		}
-	}
+	// Build messages - handle compaction ordering correctly
+	// When there's a compaction, we need to:
+	// 1. Emit summary first
+	// 2. Emit kept messages (from firstKeptEntryId up to compaction)
+	// 3. Emit messages after compaction
+	const messages: AppMessage[] = [];
 
-	if (latestCompactionIndex === -1) {
-		const messages: AppMessage[] = [];
-		for (const entry of entries) {
-			if (entry.type === "message") {
+	if (compaction) {
+		// Emit summary first
+		messages.push(createSummaryMessage(compaction.summary));
+
+		// Find compaction index in path
+		const compactionIdx = path.findIndex((e) => e.type === "compaction" && e.id === compaction.id);
+
+		// Emit kept messages (before compaction, starting from firstKeptEntryId)
+		let foundFirstKept = false;
+		for (let i = 0; i < compactionIdx; i++) {
+			const entry = path[i];
+			if (entry.id === compaction.firstKeptEntryId) {
+				foundFirstKept = true;
+			}
+			if (foundFirstKept && entry.type === "message") {
 				messages.push(entry.message);
 			}
 		}
-		return { messages, thinkingLevel, model };
-	}
 
-	const compactionEvent = entries[latestCompactionIndex] as CompactionEntry;
-
-	const keptMessages: AppMessage[] = [];
-	for (let i = compactionEvent.firstKeptEntryIndex; i < entries.length; i++) {
-		const entry = entries[i];
-		if (entry.type === "message") {
-			keptMessages.push(entry.message);
+		// Emit messages after compaction
+		for (let i = compactionIdx + 1; i < path.length; i++) {
+			const entry = path[i];
+			if (entry.type === "message") {
+				messages.push(entry.message);
+			} else if (entry.type === "branch_summary") {
+				messages.push(createSummaryMessage(entry.summary));
+			}
+		}
+	} else {
+		// No compaction - emit all messages, handle branch summaries
+		for (const entry of path) {
+			if (entry.type === "message") {
+				messages.push(entry.message);
+			} else if (entry.type === "branch_summary") {
+				messages.push(createSummaryMessage(entry.summary));
+			}
 		}
 	}
 
-	const messages: AppMessage[] = [];
-	messages.push(createSummaryMessage(compactionEvent.summary));
-	messages.push(...keptMessages);
-
 	return { messages, thinkingLevel, model };
 }
 
@@ -229,6 +361,10 @@ export class SessionManager {
 	private flushed: boolean = false;
 	private inMemoryEntries: SessionEntry[] = [];
 
+	// Tree structure (v2)
+	private byId: Map<string, ConversationEntry> = new Map();
+	private leafId: string = "";
+
 	private constructor(cwd: string, sessionDir: string, sessionFile: string | null, persist: boolean) {
 		this.cwd = cwd;
 		this.sessionDir = sessionDir;
@@ -240,10 +376,7 @@ export class SessionManager {
 		if (sessionFile) {
 			this.setSessionFile(sessionFile);
 		} else {
-			this.sessionId = uuidv4();
-			const timestamp = new Date().toISOString().replace(/[:.]/g, "-");
-			const sessionFile = join(this.getSessionDir(), `${timestamp}_${this.sessionId}.jsonl`);
-			this.setSessionFile(sessionFile);
+			this._initNewSession();
 		}
 	}
 
@@ -252,23 +385,61 @@ export class SessionManager {
 		this.sessionFile = resolve(sessionFile);
 		if (existsSync(this.sessionFile)) {
 			this.inMemoryEntries = loadEntriesFromFile(this.sessionFile);
-			const header = this.inMemoryEntries.find((e) => e.type === "session");
-			this.sessionId = header ? (header as SessionHeader).id : uuidv4();
+			const header = this.inMemoryEntries.find((e) => e.type === "session") as SessionHeader | undefined;
+			this.sessionId = header?.id ?? uuidv4();
+
+			// Migrate v1 to v2 if needed
+			const version = header?.version ?? 1;
+			if (version < CURRENT_SESSION_VERSION) {
+				this._migrateToV2();
+				this._rewriteFile();
+			}
+
+			this._buildIndex();
 			this.flushed = true;
 		} else {
-			this.sessionId = uuidv4();
-			this.inMemoryEntries = [];
-			this.flushed = false;
-			const entry: SessionHeader = {
-				type: "session",
-				id: this.sessionId,
-				timestamp: new Date().toISOString(),
-				cwd: this.cwd,
-			};
-			this.inMemoryEntries.push(entry);
+			this._initNewSession();
 		}
 	}
 
+	private _initNewSession(): void {
+		this.sessionId = uuidv4();
+		const timestamp = new Date().toISOString();
+		const header: SessionHeader = {
+			type: "session",
+			version: CURRENT_SESSION_VERSION,
+			id: this.sessionId,
+			timestamp,
+			cwd: this.cwd,
+		};
+		this.inMemoryEntries = [header];
+		this.byId.clear();
+		this.leafId = "";
+		this.flushed = false;
+		const fileTimestamp = timestamp.replace(/[:.]/g, "-");
+		this.sessionFile = join(this.getSessionDir(), `${fileTimestamp}_${this.sessionId}.jsonl`);
+	}
+
+	private _migrateToV2(): void {
+		migrateSessionEntries(this.inMemoryEntries);
+	}
+
+	private _buildIndex(): void {
+		this.byId.clear();
+		this.leafId = "";
+		for (const entry of this.inMemoryEntries) {
+			if (entry.type === "session") continue;
+			this.byId.set(entry.id, entry);
+			this.leafId = entry.id;
+		}
+	}
+
+	private _rewriteFile(): void {
+		if (!this.persist) return;
+		const content = `${this.inMemoryEntries.map((e) => JSON.stringify(e)).join("\n")}\n`;
+		writeFileSync(this.sessionFile, content);
+	}
+
 	isPersisted(): boolean {
 		return this.persist;
 	}
@@ -290,18 +461,7 @@ export class SessionManager {
 	}
 
 	reset(): void {
-		this.sessionId = uuidv4();
-		this.flushed = false;
-		const timestamp = new Date().toISOString().replace(/[:.]/g, "-");
-		this.sessionFile = join(this.getSessionDir(), `${timestamp}_${this.sessionId}.jsonl`);
-		this.inMemoryEntries = [
-			{
-				type: "session",
-				id: this.sessionId,
-				timestamp: new Date().toISOString(),
-				cwd: this.cwd,
-			},
-		];
+		this._initNewSession();
 	}
 
 	_persist(entry: SessionEntry): void {
@@ -320,49 +480,93 @@ export class SessionManager {
 		}
 	}
 
-	saveMessage(message: AppMessage): void {
+	private _appendEntry(entry: ConversationEntry): void {
+		this.inMemoryEntries.push(entry);
+		this.byId.set(entry.id, entry);
+		this.leafId = entry.id;
+		this._persist(entry);
+	}
+
+	saveMessage(message: AppMessage): string {
 		const entry: SessionMessageEntry = {
 			type: "message",
+			id: uuidv4(),
+			parentId: this.leafId || null,
 			timestamp: new Date().toISOString(),
 			message,
 		};
-		this.inMemoryEntries.push(entry);
-		this._persist(entry);
+		this._appendEntry(entry);
+		return entry.id;
 	}
 
-	saveThinkingLevelChange(thinkingLevel: string): void {
+	saveThinkingLevelChange(thinkingLevel: string): string {
 		const entry: ThinkingLevelChangeEntry = {
 			type: "thinking_level_change",
+			id: uuidv4(),
+			parentId: this.leafId || null,
 			timestamp: new Date().toISOString(),
 			thinkingLevel,
 		};
-		this.inMemoryEntries.push(entry);
-		this._persist(entry);
+		this._appendEntry(entry);
+		return entry.id;
 	}
 
-	saveModelChange(provider: string, modelId: string): void {
+	saveModelChange(provider: string, modelId: string): string {
 		const entry: ModelChangeEntry = {
 			type: "model_change",
+			id: uuidv4(),
+			parentId: this.leafId || null,
 			timestamp: new Date().toISOString(),
 			provider,
 			modelId,
 		};
-		this.inMemoryEntries.push(entry);
-		this._persist(entry);
+		this._appendEntry(entry);
+		return entry.id;
 	}
 
-	saveCompaction(entry: CompactionEntry): void {
-		this.inMemoryEntries.push(entry);
-		this._persist(entry);
+	saveCompaction(summary: string, firstKeptEntryId: string, tokensBefore: number): string {
+		const entry: CompactionEntry = {
+			type: "compaction",
+			id: uuidv4(),
+			parentId: this.leafId || null,
+			timestamp: new Date().toISOString(),
+			summary,
+			firstKeptEntryId,
+			tokensBefore,
+		};
+		this._appendEntry(entry);
+		return entry.id;
+	}
+
+	// =========================================================================
+	// Tree Traversal
+	// =========================================================================
+
+	getLeafUuid(): string {
+		return this.leafId;
+	}
+
+	getEntry(id: string): ConversationEntry | undefined {
+		return this.byId.get(id);
+	}
+
+	/** Walk from entry to root, returning path (conversation entries only) */
+	getPath(fromId?: string): ConversationEntry[] {
+		const path: ConversationEntry[] = [];
+		let current = this.byId.get(fromId ?? this.leafId);
+		while (current) {
+			path.unshift(current);
+			current = current.parentId ? this.byId.get(current.parentId) : undefined;
+		}
+		return path;
 	}
 
 	/**
 	 * Build the session context (what gets sent to the LLM).
-	 * If compacted, returns summary + kept messages. Otherwise all messages.
-	 * Includes thinking level and model.
+	 * Uses tree traversal from current leaf.
 	 */
 	buildSessionContext(): SessionContext {
-		return buildSessionContext(this.getEntries());
+		return buildSessionContext(this.getEntries(), this.leafId);
 	}
 
 	/**
@@ -373,6 +577,35 @@ export class SessionManager {
 		return [...this.inMemoryEntries];
 	}
 
+	// =========================================================================
+	// Branching
+	// =========================================================================
+
+	/** Branch in-place by changing the leaf pointer */
+	branchInPlace(branchFromId: string): void {
+		if (!this.byId.has(branchFromId)) {
+			throw new Error(`Entry ${branchFromId} not found`);
+		}
+		this.leafId = branchFromId;
+	}
+
+	/** Branch with a summary of the abandoned path */
+	branchWithSummary(branchFromId: string, summary: string): string {
+		if (!this.byId.has(branchFromId)) {
+			throw new Error(`Entry ${branchFromId} not found`);
+		}
+		this.leafId = branchFromId;
+		const entry: BranchSummaryEntry = {
+			type: "branch_summary",
+			id: uuidv4(),
+			parentId: branchFromId,
+			timestamp: new Date().toISOString(),
+			summary,
+		};
+		this._appendEntry(entry);
+		return entry.id;
+	}
+
 	createBranchedSessionFromEntries(entries: SessionEntry[], branchBeforeIndex: number): string | null {
 		const newSessionId = uuidv4();
 		const timestamp = new Date().toISOString().replace(/[:.]/g, "-");
@@ -385,6 +618,7 @@ export class SessionManager {
 			if (entry.type === "session") {
 				newEntries.push({
 					...entry,
+					version: CURRENT_SESSION_VERSION,
 					id: newSessionId,
 					timestamp: new Date().toISOString(),
 					branchedFrom: this.persist ? this.sessionFile : undefined,
@@ -402,6 +636,7 @@ export class SessionManager {
 		}
 		this.inMemoryEntries = newEntries;
 		this.sessionId = newSessionId;
+		this._buildIndex();
 		return null;
 	}
 
diff --git a/packages/coding-agent/src/index.ts b/packages/coding-agent/src/index.ts
index 2683765e..04151f0b 100644
--- a/packages/coding-agent/src/index.ts
+++ b/packages/coding-agent/src/index.ts
@@ -107,11 +107,20 @@ export {
 	readOnlyTools,
 } from "./core/sdk.js";
 export {
+	type BranchSummaryContent,
+	type BranchSummaryEntry,
 	buildSessionContext,
+	type CompactionContent,
 	type CompactionEntry,
+	type ConversationContent,
+	type ConversationEntry,
+	CURRENT_SESSION_VERSION,
 	createSummaryMessage,
 	getLatestCompactionEntry,
+	type MessageContent,
+	type ModelChangeContent,
 	type ModelChangeEntry,
+	migrateSessionEntries,
 	parseSessionEntries,
 	type SessionContext as LoadedSession,
 	type SessionEntry,
@@ -122,6 +131,9 @@ export {
 	SUMMARY_PREFIX,
 	SUMMARY_SUFFIX,
 	type ThinkingLevelChangeEntry,
+	type ThinkingLevelContent,
+	// Tree types (v2)
+	type TreeNode,
 } from "./core/session-manager.js";
 export {
 	type CompactionSettings,
diff --git a/packages/coding-agent/test/agent-session-compaction.test.ts b/packages/coding-agent/test/agent-session-compaction.test.ts
index ff519eb5..2b7f5e71 100644
--- a/packages/coding-agent/test/agent-session-compaction.test.ts
+++ b/packages/coding-agent/test/agent-session-compaction.test.ts
@@ -156,9 +156,9 @@ describe.skipIf(!API_KEY)("AgentSession compaction e2e", () => {
 		expect(compaction.type).toBe("compaction");
 		if (compaction.type === "compaction") {
 			expect(compaction.summary.length).toBeGreaterThan(0);
-			// firstKeptEntryIndex can be 0 if all messages fit within keepRecentTokens
+			// firstKeptEntryId can be 0 if all messages fit within keepRecentTokens
 			// (which is the case for small conversations)
-			expect(compaction.firstKeptEntryIndex).toBeGreaterThanOrEqual(0);
+			expect(compaction.firstKeptEntryId).toBeGreaterThanOrEqual(0);
 			expect(compaction.tokensBefore).toBeGreaterThan(0);
 		}
 	}, 120000);
diff --git a/packages/coding-agent/test/compaction-hooks-example.test.ts b/packages/coding-agent/test/compaction-hooks-example.test.ts
index 476d40fb..9c5f5479 100644
--- a/packages/coding-agent/test/compaction-hooks-example.test.ts
+++ b/packages/coding-agent/test/compaction-hooks-example.test.ts
@@ -4,7 +4,6 @@
 
 import { describe, expect, it } from "vitest";
 import type { HookAPI } from "../src/core/hooks/index.js";
-import type { CompactionEntry } from "../src/core/session-manager.js";
 
 describe("Documentation example", () => {
 	it("custom compaction example should type-check correctly", () => {
@@ -20,29 +19,30 @@ describe("Documentation example", () => {
 				const tokensBefore = event.tokensBefore;
 				const model = event.model;
 				const resolveApiKey = event.resolveApiKey;
+				const firstKeptEntryId = event.firstKeptEntryId;
 
 				// Verify types
 				expect(Array.isArray(messages)).toBe(true);
 				expect(Array.isArray(messagesToKeep)).toBe(true);
-				expect(typeof cutPoint.firstKeptEntryIndex).toBe("number");
+				expect(typeof cutPoint.firstKeptEntryIndex).toBe("number"); // cutPoint still uses index
 				expect(typeof tokensBefore).toBe("number");
 				expect(model).toBeDefined();
 				expect(typeof resolveApiKey).toBe("function");
+				expect(typeof firstKeptEntryId).toBe("string");
 
 				const summary = messages
 					.filter((m) => m.role === "user")
 					.map((m) => `- ${typeof m.content === "string" ? m.content.slice(0, 100) : "[complex]"}`)
 					.join("\n");
 
-				const compactionEntry: CompactionEntry = {
-					type: "compaction",
-					timestamp: new Date().toISOString(),
-					summary: `User requests:\n${summary}`,
-					firstKeptEntryIndex: event.cutPoint.firstKeptEntryIndex,
-					tokensBefore: event.tokensBefore,
+				// Hooks return compaction content - SessionManager adds id/parentId
+				return {
+					compaction: {
+						summary: `User requests:\n${summary}`,
+						firstKeptEntryId,
+						tokensBefore,
+					},
 				};
-
-				return { compactionEntry };
 			});
 		};
 
diff --git a/packages/coding-agent/test/compaction.test.ts b/packages/coding-agent/test/compaction.test.ts
index 24c7e89d..787e863e 100644
--- a/packages/coding-agent/test/compaction.test.ts
+++ b/packages/coding-agent/test/compaction.test.ts
@@ -3,7 +3,7 @@ import type { AssistantMessage, Usage } from "@mariozechner/pi-ai";
 import { getModel } from "@mariozechner/pi-ai";
 import { readFileSync } from "fs";
 import { join } from "path";
-import { describe, expect, it } from "vitest";
+import { beforeEach, describe, expect, it } from "vitest";
 import {
 	type CompactionSettings,
 	calculateContextTokens,
@@ -17,9 +17,12 @@ import {
 	buildSessionContext,
 	type CompactionEntry,
 	createSummaryMessage,
+	type ModelChangeEntry,
+	migrateSessionEntries,
 	parseSessionEntries,
 	type SessionEntry,
 	type SessionMessageEntry,
+	type ThinkingLevelChangeEntry,
 } from "../src/core/session-manager.js";
 
 // ============================================================================
@@ -29,7 +32,9 @@ import {
 function loadLargeSessionEntries(): SessionEntry[] {
 	const sessionPath = join(__dirname, "fixtures/large-session.jsonl");
 	const content = readFileSync(sessionPath, "utf-8");
-	return parseSessionEntries(content);
+	const entries = parseSessionEntries(content);
+	migrateSessionEntries(entries); // Add id/parentId for v1 fixtures
+	return entries;
 }
 
 function createMockUsage(input: number, output: number, cacheRead = 0, cacheWrite = 0): Usage {
@@ -60,18 +65,82 @@ function createAssistantMessage(text: string, usage?: Usage): AssistantMessage {
 	};
 }
 
-function createMessageEntry(message: AppMessage): SessionMessageEntry {
-	return { type: "message", timestamp: new Date().toISOString(), message };
+let entryCounter = 0;
+let lastId: string | null = null;
+
+function resetEntryCounter() {
+	entryCounter = 0;
+	lastId = null;
 }
 
-function createCompactionEntry(summary: string, firstKeptEntryIndex: number): CompactionEntry {
+// Reset counter before each test to get predictable IDs
+beforeEach(() => {
+	resetEntryCounter();
+});
+
+function createSessionHeader() {
 	return {
+		type: "session" as const,
+		version: 2,
+		id: "test-session",
+		timestamp: "",
+		cwd: "",
+	};
+}
+
+function createMessageEntry(message: AppMessage): SessionMessageEntry {
+	const id = `test-id-${entryCounter++}`;
+	const entry: SessionMessageEntry = {
+		type: "message",
+		id,
+		parentId: lastId,
+		timestamp: new Date().toISOString(),
+		message,
+	};
+	lastId = id;
+	return entry;
+}
+
+function createCompactionEntry(summary: string, firstKeptEntryId: string): CompactionEntry {
+	const id = `test-id-${entryCounter++}`;
+	const entry: CompactionEntry = {
 		type: "compaction",
+		id,
+		parentId: lastId,
 		timestamp: new Date().toISOString(),
 		summary,
-		firstKeptEntryIndex,
+		firstKeptEntryId,
 		tokensBefore: 10000,
 	};
+	lastId = id;
+	return entry;
+}
+
+function createModelChangeEntry(provider: string, modelId: string): ModelChangeEntry {
+	const id = `test-id-${entryCounter++}`;
+	const entry: ModelChangeEntry = {
+		type: "model_change",
+		id,
+		parentId: lastId,
+		timestamp: new Date().toISOString(),
+		provider,
+		modelId,
+	};
+	lastId = id;
+	return entry;
+}
+
+function createThinkingLevelEntry(thinkingLevel: string): ThinkingLevelChangeEntry {
+	const id = `test-id-${entryCounter++}`;
+	const entry: ThinkingLevelChangeEntry = {
+		type: "thinking_level_change",
+		id,
+		parentId: lastId,
+		timestamp: new Date().toISOString(),
+		thinkingLevel,
+	};
+	lastId = id;
+	return entry;
 }
 
 // ============================================================================
@@ -248,78 +317,59 @@ describe("buildSessionContext", () => {
 	});
 
 	it("should handle single compaction", () => {
-		// indices: 0=session, 1=u1, 2=a1, 3=u2, 4=a2, 5=compaction, 6=u3, 7=a3
-		const entries: SessionEntry[] = [
-			{
-				type: "session",
-				id: "1",
-				timestamp: "",
-				cwd: "",
-			},
-			createMessageEntry(createUserMessage("1")),
-			createMessageEntry(createAssistantMessage("a")),
-			createMessageEntry(createUserMessage("2")),
-			createMessageEntry(createAssistantMessage("b")),
-			createCompactionEntry("Summary of 1,a,2,b", 3), // keep from index 3 (u2) onwards
-			createMessageEntry(createUserMessage("3")),
-			createMessageEntry(createAssistantMessage("c")),
-		];
+		// IDs: u1=test-id-0, a1=test-id-1, u2=test-id-2, a2=test-id-3, compaction=test-id-4, u3=test-id-5, a3=test-id-6
+		const u1 = createMessageEntry(createUserMessage("1"));
+		const a1 = createMessageEntry(createAssistantMessage("a"));
+		const u2 = createMessageEntry(createUserMessage("2"));
+		const a2 = createMessageEntry(createAssistantMessage("b"));
+		const compaction = createCompactionEntry("Summary of 1,a,2,b", u2.id); // keep from u2 onwards
+		const u3 = createMessageEntry(createUserMessage("3"));
+		const a3 = createMessageEntry(createAssistantMessage("c"));
+
+		const entries: SessionEntry[] = [createSessionHeader(), u1, a1, u2, a2, compaction, u3, a3];
 
 		const loaded = buildSessionContext(entries);
-		// summary + kept (u2,a2 from idx 3-4) + after (u3,a3 from idx 6-7) = 5
+		// summary + kept (u2, a2) + after (u3, a3) = 5
 		expect(loaded.messages.length).toBe(5);
 		expect(loaded.messages[0].role).toBe("user");
 		expect((loaded.messages[0] as any).content).toContain("Summary of 1,a,2,b");
 	});
 
 	it("should handle multiple compactions (only latest matters)", () => {
-		// indices: 0=session, 1=u1, 2=a1, 3=compact1, 4=u2, 5=b, 6=u3, 7=c, 8=compact2, 9=u4, 10=d
-		const entries: SessionEntry[] = [
-			{
-				type: "session",
-				id: "1",
-				timestamp: "",
-				cwd: "",
-			},
-			createMessageEntry(createUserMessage("1")),
-			createMessageEntry(createAssistantMessage("a")),
-			createCompactionEntry("First summary", 1), // keep from index 1
-			createMessageEntry(createUserMessage("2")),
-			createMessageEntry(createAssistantMessage("b")),
-			createMessageEntry(createUserMessage("3")),
-			createMessageEntry(createAssistantMessage("c")),
-			createCompactionEntry("Second summary", 6), // keep from index 6 (u3) onwards
-			createMessageEntry(createUserMessage("4")),
-			createMessageEntry(createAssistantMessage("d")),
-		];
+		// First batch
+		const u1 = createMessageEntry(createUserMessage("1"));
+		const a1 = createMessageEntry(createAssistantMessage("a"));
+		const compact1 = createCompactionEntry("First summary", u1.id);
+		// Second batch
+		const u2 = createMessageEntry(createUserMessage("2"));
+		const b = createMessageEntry(createAssistantMessage("b"));
+		const u3 = createMessageEntry(createUserMessage("3"));
+		const c = createMessageEntry(createAssistantMessage("c"));
+		const compact2 = createCompactionEntry("Second summary", u3.id); // keep from u3 onwards
+		// After second compaction
+		const u4 = createMessageEntry(createUserMessage("4"));
+		const d = createMessageEntry(createAssistantMessage("d"));
+
+		const entries: SessionEntry[] = [createSessionHeader(), u1, a1, compact1, u2, b, u3, c, compact2, u4, d];
 
 		const loaded = buildSessionContext(entries);
-		// summary + kept from idx 6 (u3,c) + after (u4,d) = 5
+		// summary + kept from u3 (u3, c) + after (u4, d) = 5
 		expect(loaded.messages.length).toBe(5);
 		expect((loaded.messages[0] as any).content).toContain("Second summary");
 	});
 
-	it("should clamp firstKeptEntryIndex to valid range", () => {
-		// indices: 0=session, 1=u1, 2=a1, 3=compact1, 4=u2, 5=b, 6=compact2
-		const entries: SessionEntry[] = [
-			{
-				type: "session",
-				id: "1",
-				timestamp: "",
-				cwd: "",
-			},
-			createMessageEntry(createUserMessage("1")),
-			createMessageEntry(createAssistantMessage("a")),
-			createCompactionEntry("First summary", 1),
-			createMessageEntry(createUserMessage("2")),
-			createMessageEntry(createAssistantMessage("b")),
-			createCompactionEntry("Second summary", 0), // index 0 is before compaction1, should still work
-		];
+	it("should keep all messages when firstKeptEntryId is first entry", () => {
+		const u1 = createMessageEntry(createUserMessage("1"));
+		const a1 = createMessageEntry(createAssistantMessage("a"));
+		const compact1 = createCompactionEntry("First summary", u1.id); // keep from first entry
+		const u2 = createMessageEntry(createUserMessage("2"));
+		const b = createMessageEntry(createAssistantMessage("b"));
+
+		const entries: SessionEntry[] = [createSessionHeader(), u1, a1, compact1, u2, b];
 
 		const loaded = buildSessionContext(entries);
-		// Keeps from index 0, but compaction entries are skipped, so u1,a1,u2,b = 4 + summary = 5
-		// Actually index 0 is session header, so messages are u1,a1,u2,b
-		expect(loaded.messages.length).toBe(5); // summary + 4 messages
+		// summary + all messages (u1, a1, u2, b) = 5
+		expect(loaded.messages.length).toBe(5);
 	});
 
 	it("should track model and thinking level changes", () => {
@@ -331,9 +381,9 @@ describe("buildSessionContext", () => {
 				cwd: "",
 			},
 			createMessageEntry(createUserMessage("1")),
-			{ type: "model_change", timestamp: "", provider: "openai", modelId: "gpt-4" },
+			createModelChangeEntry("openai", "gpt-4"),
 			createMessageEntry(createAssistantMessage("a")),
-			{ type: "thinking_level_change", timestamp: "", thinkingLevel: "high" },
+			createThinkingLevelEntry("high"),
 		];
 
 		const loaded = buildSessionContext(entries);
@@ -380,27 +430,26 @@ describe("Large session fixture", () => {
 // ============================================================================
 
 describe.skipIf(!process.env.ANTHROPIC_OAUTH_TOKEN)("LLM summarization", () => {
-	it("should generate a compaction event for the large session", async () => {
+	it("should generate a compaction result for the large session", async () => {
 		const entries = loadLargeSessionEntries();
 		const model = getModel("anthropic", "claude-sonnet-4-5")!;
 
-		const compactionEvent = await compact(
+		const compactionResult = await compact(
 			entries,
 			model,
 			DEFAULT_COMPACTION_SETTINGS,
 			process.env.ANTHROPIC_OAUTH_TOKEN!,
 		);
 
-		expect(compactionEvent.type).toBe("compaction");
-		expect(compactionEvent.summary.length).toBeGreaterThan(100);
-		expect(compactionEvent.firstKeptEntryIndex).toBeGreaterThan(0);
-		expect(compactionEvent.tokensBefore).toBeGreaterThan(0);
+		expect(compactionResult.summary.length).toBeGreaterThan(100);
+		expect(compactionResult.firstKeptEntryId).toBeTruthy();
+		expect(compactionResult.tokensBefore).toBeGreaterThan(0);
 
-		console.log("Summary length:", compactionEvent.summary.length);
-		console.log("First kept entry index:", compactionEvent.firstKeptEntryIndex);
-		console.log("Tokens before:", compactionEvent.tokensBefore);
+		console.log("Summary length:", compactionResult.summary.length);
+		console.log("First kept entry ID:", compactionResult.firstKeptEntryId);
+		console.log("Tokens before:", compactionResult.tokensBefore);
 		console.log("\n--- SUMMARY ---\n");
-		console.log(compactionEvent.summary);
+		console.log(compactionResult.summary);
 	}, 60000);
 
 	it("should produce valid session after compaction", async () => {
@@ -408,21 +457,30 @@ describe.skipIf(!process.env.ANTHROPIC_OAUTH_TOKEN)("LLM summarization", () => {
 		const loaded = buildSessionContext(entries);
 		const model = getModel("anthropic", "claude-sonnet-4-5")!;
 
-		const compactionEvent = await compact(
+		const compactionResult = await compact(
 			entries,
 			model,
 			DEFAULT_COMPACTION_SETTINGS,
 			process.env.ANTHROPIC_OAUTH_TOKEN!,
 		);
 
-		// Simulate appending compaction to entries
-		const newEntries = [...entries, compactionEvent];
+		// Simulate appending compaction to entries by creating a proper entry
+		const lastEntry = entries[entries.length - 1];
+		const parentId = lastEntry.type === "session" ? null : lastEntry.id;
+		const compactionEntry: CompactionEntry = {
+			type: "compaction",
+			id: "compaction-test-id",
+			parentId,
+			timestamp: new Date().toISOString(),
+			...compactionResult,
+		};
+		const newEntries = [...entries, compactionEntry];
 		const reloaded = buildSessionContext(newEntries);
 
 		// Should have summary + kept messages
 		expect(reloaded.messages.length).toBeLessThan(loaded.messages.length);
 		expect(reloaded.messages[0].role).toBe("user");
-		expect((reloaded.messages[0] as any).content).toContain(compactionEvent.summary);
+		expect((reloaded.messages[0] as any).content).toContain(compactionResult.summary);
 
 		console.log("Original messages:", loaded.messages.length);
 		console.log("After compaction:", reloaded.messages.length);
diff --git a/packages/mom/src/context.ts b/packages/mom/src/context.ts
index 00920ae4..2e24bf5a 100644
--- a/packages/mom/src/context.ts
+++ b/packages/mom/src/context.ts
@@ -15,10 +15,14 @@ import {
 	buildSessionContext,
 	type CompactionEntry,
 	type LoadedSession,
+	type MessageContent,
+	type ModelChangeContent,
 	type ModelChangeEntry,
 	type SessionEntry,
 	type SessionMessageEntry,
 	type ThinkingLevelChangeEntry,
+	type ThinkingLevelContent,
+	type TreeNode,
 } from "@mariozechner/pi-coding-agent";
 import { randomBytes } from "crypto";
 import { appendFileSync, existsSync, mkdirSync, readFileSync, writeFileSync } from "fs";
@@ -49,6 +53,7 @@ export class MomSessionManager {
 	private channelDir: string;
 	private flushed: boolean = false;
 	private inMemoryEntries: SessionEntry[] = [];
+	private leafId: string | null = null;
 
 	constructor(channelDir: string) {
 		this.channelDir = channelDir;
@@ -64,12 +69,14 @@ export class MomSessionManager {
 		if (existsSync(this.contextFile)) {
 			this.inMemoryEntries = this.loadEntriesFromFile();
 			this.sessionId = this.extractSessionId() || uuidv4();
+			this._updateLeafId();
 			this.flushed = true;
 		} else {
 			this.sessionId = uuidv4();
 			this.inMemoryEntries = [
 				{
 					type: "session",
+					version: 2,
 					id: this.sessionId,
 					timestamp: new Date().toISOString(),
 					cwd: this.channelDir,
@@ -79,6 +86,28 @@ export class MomSessionManager {
 		// Note: syncFromLog() is called explicitly from agent.ts with excludeTimestamp
 	}
 
+	private _updateLeafId(): void {
+		for (let i = this.inMemoryEntries.length - 1; i >= 0; i--) {
+			const entry = this.inMemoryEntries[i];
+			if (entry.type !== "session") {
+				this.leafId = entry.id;
+				return;
+			}
+		}
+		this.leafId = null;
+	}
+
+	private _createTreeNode(): TreeNode {
+		const id = uuidv4();
+		const node: TreeNode = {
+			id,
+			parentId: this.leafId,
+			timestamp: new Date().toISOString(),
+		};
+		this.leafId = id;
+		return node;
+	}
+
 	private _persist(entry: SessionEntry): void {
 		const hasAssistant = this.inMemoryEntries.some((e) => e.type === "message" && e.message.role === "assistant");
 		if (!hasAssistant) return;
@@ -206,11 +235,15 @@ export class MomSessionManager {
 		newMessages.sort((a, b) => new Date(a.timestamp).getTime() - new Date(b.timestamp).getTime());
 
 		for (const { timestamp, message } of newMessages) {
+			const id = uuidv4();
 			const entry: SessionMessageEntry = {
 				type: "message",
+				id,
+				parentId: this.leafId,
 				timestamp, // Use log date as entry timestamp for consistent deduplication
 				message,
 			};
+			this.leafId = id;
 
 			this.inMemoryEntries.push(entry);
 			appendFileSync(this.contextFile, `${JSON.stringify(entry)}\n`);
@@ -247,32 +280,22 @@ export class MomSessionManager {
 	}
 
 	saveMessage(message: AppMessage): void {
-		const entry: SessionMessageEntry = {
-			type: "message",
-			timestamp: new Date().toISOString(),
-			message,
-		};
+		const content: MessageContent = { type: "message", message };
+		const entry: SessionMessageEntry = { ...this._createTreeNode(), ...content };
 		this.inMemoryEntries.push(entry);
 		this._persist(entry);
 	}
 
 	saveThinkingLevelChange(thinkingLevel: string): void {
-		const entry: ThinkingLevelChangeEntry = {
-			type: "thinking_level_change",
-			timestamp: new Date().toISOString(),
-			thinkingLevel,
-		};
+		const content: ThinkingLevelContent = { type: "thinking_level_change", thinkingLevel };
+		const entry: ThinkingLevelChangeEntry = { ...this._createTreeNode(), ...content };
 		this.inMemoryEntries.push(entry);
 		this._persist(entry);
 	}
 
 	saveModelChange(provider: string, modelId: string): void {
-		const entry: ModelChangeEntry = {
-			type: "model_change",
-			timestamp: new Date().toISOString(),
-			provider,
-			modelId,
-		};
+		const content: ModelChangeContent = { type: "model_change", provider, modelId };
+		const entry: ModelChangeEntry = { ...this._createTreeNode(), ...content };
 		this.inMemoryEntries.push(entry);
 		this._persist(entry);
 	}