diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts
index f3d885b7..4c98e5ac 100644
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -5,26 +5,9 @@ import type { Model } from "./types.js";
 
 export const MODELS = {
 	anthropic: {
-		"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-3-sonnet-20240229": {
-			id: "claude-3-sonnet-20240229",
-			name: "Claude Sonnet 3",
+		"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",
@@ -34,61 +17,10 @@ export const MODELS = {
 				input: 3,
 				output: 15,
 				cacheRead: 0.3,
-				cacheWrite: 0.3,
+				cacheWrite: 3.75,
 			},
 			contextWindow: 200000,
-			maxTokens: 4096,
-		} 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-opus-20240229": {
-			id: "claude-3-opus-20240229",
-			name: "Claude Opus 3",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 15,
-				output: 75,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 4096,
-		} 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,
+			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
 		"claude-3-5-sonnet-20240620": {
 			id: "claude-3-5-sonnet-20240620",
@@ -107,65 +39,14 @@ export const MODELS = {
 			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",
+		"claude-3-opus-20240229": {
+			id: "claude-3-opus-20240229",
+			name: "Claude Opus 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: 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",
-			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-3-5-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-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,
@@ -173,7 +54,7 @@ export const MODELS = {
 				cacheWrite: 18.75,
 			},
 			contextWindow: 200000,
-			maxTokens: 32000,
+			maxTokens: 4096,
 		} satisfies Model<"anthropic-messages">,
 		"claude-sonnet-4-5-20250929": {
 			id: "claude-sonnet-4-5-20250929",
@@ -209,6 +90,159 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} 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-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">,
+		"claude-sonnet-4-0": {
+			id: "claude-sonnet-4-0",
+			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-3-7-sonnet-latest": {
+			id: "claude-3-7-sonnet-latest",
+			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-sonnet-4-5": {
 			id: "claude-sonnet-4-5",
 			name: "Claude Sonnet 4.5",
@@ -243,57 +277,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
-		"claude-opus-4-1": {
-			id: "claude-opus-4-1",
-			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-sonnet-4-0": {
-			id: "claude-sonnet-4-0",
-			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-3-7-sonnet-latest": {
-			id: "claude-3-7-sonnet-latest",
-			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-haiku-4-5": {
 			id: "claude-haiku-4-5",
 			name: "Claude Haiku 4.5",
@@ -311,6 +294,23 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
+		"claude-opus-4-1": {
+			id: "claude-opus-4-1",
+			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-4-0": {
 			id: "claude-opus-4-0",
 			name: "Claude Opus 4",
@@ -330,142 +330,6 @@ export const MODELS = {
 		} satisfies Model<"anthropic-messages">,
 	},
 	google: {
-		"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-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-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-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-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-2.0-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-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-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-2.5-flash-preview-05-20": {
 			id: "gemini-2.5-flash-preview-05-20",
 			name: "Gemini 2.5 Flash Preview 05-20",
@@ -483,9 +347,9 @@ export const MODELS = {
 			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",
+		"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",
@@ -517,43 +381,26 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"google-generative-ai">,
-		"gemini-1.5-flash-8b": {
-			id: "gemini-1.5-flash-8b",
-			name: "Gemini 1.5 Flash-8B",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.0375,
-				output: 0.15,
-				cacheRead: 0.01,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			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",
+		"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"],
+			input: ["text", "image"],
 			cost: {
-				input: 0.5,
-				output: 2,
-				cacheRead: 0,
+				input: 0.3,
+				output: 2.5,
+				cacheRead: 0.075,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
+			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"google-generative-ai">,
-		"gemini-2.5-pro": {
-			id: "gemini-2.5-pro",
-			name: "Gemini 2.5 Pro",
+		"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",
@@ -585,9 +432,43 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 8192,
 		} 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",
+		"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",
@@ -602,6 +483,108 @@ export const MODELS = {
 			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",
@@ -619,62 +602,130 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 8192,
 		} 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",
+		"gemini-1.5-flash-8b": {
+			id: "gemini-1.5-flash-8b",
+			name: "Gemini 1.5 Flash-8B",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.0375,
+				output: 0.15,
+				cacheRead: 0.01,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 8192,
+		} 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",
 			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,
+				input: 0.1,
+				output: 0.4,
+				cacheRead: 0.025,
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"google-generative-ai">,
-		"gemini-flash-latest": {
-			id: "gemini-flash-latest",
-			name: "Gemini Flash Latest",
+		"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,
+			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.3,
-				output: 2.5,
-				cacheRead: 0.075,
+				input: 1.25,
+				output: 5,
+				cacheRead: 0.3125,
 				cacheWrite: 0,
 			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
+			contextWindow: 1000000,
+			maxTokens: 8192,
 		} satisfies Model<"google-generative-ai">,
 	},
 	openai: {
-		"gpt-5": {
-			id: "gpt-5",
-			name: "GPT-5",
+		"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-4": {
+			id: "gpt-4",
+			name: "GPT-4",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 30,
+				output: 60,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
+			maxTokens: 8192,
+		} 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: 1.25,
-				output: 10,
-				cacheRead: 0.13,
+				input: 150,
+				output: 600,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 400000,
-			maxTokens: 128000,
+			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)",
+		"gpt-4o-2024-05-13": {
+			id: "gpt-4o-2024-05-13",
+			name: "GPT-4o (2024-05-13)",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 5,
+				output: 15,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-responses">,
+		"gpt-4o-2024-08-06": {
+			id: "gpt-4o-2024-08-06",
+			name: "GPT-4o (2024-08-06)",
 			api: "openai-responses",
 			provider: "openai",
 			baseUrl: "https://api.openai.com/v1",
@@ -689,35 +740,86 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 16384,
 		} satisfies Model<"openai-responses">,
-		"o4-mini-deep-research": {
-			id: "o4-mini-deep-research",
-			name: "o4-mini-deep-research",
+		"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: 2,
-				output: 8,
-				cacheRead: 0.5,
+				input: 10,
+				output: 40,
+				cacheRead: 2.5,
 				cacheWrite: 0,
 			},
 			contextWindow: 200000,
 			maxTokens: 100000,
 		} satisfies Model<"openai-responses">,
-		o3: {
-			id: "o3",
-			name: "o3",
+		"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">,
+		"o3-mini": {
+			id: "o3-mini",
+			name: "o3-mini",
 			api: "openai-responses",
 			provider: "openai",
 			baseUrl: "https://api.openai.com/v1",
 			reasoning: true,
-			input: ["text", "image"],
+			input: ["text"],
 			cost: {
-				input: 2,
-				output: 8,
-				cacheRead: 0.5,
+				input: 1.1,
+				output: 4.4,
+				cacheRead: 0.55,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} 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,
@@ -740,40 +842,6 @@ export const MODELS = {
 			contextWindow: 400000,
 			maxTokens: 128000,
 		} 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">,
-		"gpt-4": {
-			id: "gpt-4",
-			name: "GPT-4",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 30,
-				output: 60,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 8192,
-			maxTokens: 8192,
-		} satisfies Model<"openai-responses">,
 		"gpt-5-codex": {
 			id: "gpt-5-codex",
 			name: "GPT-5-Codex",
@@ -791,18 +859,52 @@ export const MODELS = {
 			contextWindow: 400000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
-		"o3-pro": {
-			id: "o3-pro",
-			name: "o3-pro",
+		"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: 20,
-				output: 80,
-				cacheRead: 0,
+				input: 1.1,
+				output: 4.4,
+				cacheRead: 0.28,
 				cacheWrite: 0,
 			},
 			contextWindow: 200000,
@@ -825,142 +927,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 100000,
 		} satisfies Model<"openai-responses">,
-		"gpt-4o-mini": {
-			id: "gpt-4o-mini",
-			name: "GPT-4o mini",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.15,
-				output: 0.6,
-				cacheRead: 0.08,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} 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-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-4o-2024-05-13": {
-			id: "gpt-4o-2024-05-13",
-			name: "GPT-4o (2024-05-13)",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 5,
-				output: 15,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} 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">,
-		"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">,
-		"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-mini": {
 			id: "gpt-5-mini",
 			name: "GPT-5 Mini",
@@ -978,60 +944,26 @@ export const MODELS = {
 			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">,
-		"o3-deep-research": {
-			id: "o3-deep-research",
-			name: "o3-deep-research",
+		"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: 10,
-				output: 40,
-				cacheRead: 2.5,
+				input: 20,
+				output: 80,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 200000,
 			maxTokens: 100000,
 		} 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-2024-08-06": {
-			id: "gpt-4o-2024-08-06",
-			name: "GPT-4o (2024-08-06)",
+		"gpt-4o-2024-11-20": {
+			id: "gpt-4o-2024-11-20",
+			name: "GPT-4o (2024-11-20)",
 			api: "openai-responses",
 			provider: "openai",
 			baseUrl: "https://api.openai.com/v1",
@@ -1046,6 +978,74 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 16384,
 		} 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",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.15,
+				output: 0.6,
+				cacheRead: 0.08,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-responses">,
+		"gpt-5": {
+			id: "gpt-5",
+			name: "GPT-5",
+			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">,
 		"gpt-5-chat-latest": {
 			id: "gpt-5-chat-latest",
 			name: "GPT-5 Chat Latest",
@@ -1065,34 +1065,51 @@ export const MODELS = {
 		} satisfies Model<"openai-responses">,
 	},
 	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",
+		"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: 0.2,
-				output: 0.2,
+				input: 0.05,
+				output: 0.08,
+				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">,
+		"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,
 			},
@@ -1133,57 +1150,40 @@ export const MODELS = {
 			contextWindow: 8192,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"mistral-saba-24b": {
-			id: "mistral-saba-24b",
-			name: "Mistral Saba 24B",
+		"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: false,
+			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.79,
-				output: 0.79,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			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">,
-		"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,
+				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",
@@ -1201,6 +1201,74 @@ export const MODELS = {
 			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",
@@ -1252,74 +1320,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 8192,
 		} 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">,
-		"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">,
 	},
 	cerebras: {
 		"qwen-3-235b-a22b-instruct-2507": {
@@ -1375,52 +1375,35 @@ export const MODELS = {
 		} satisfies Model<"openai-completions">,
 	},
 	xai: {
-		"grok-3-mini": {
-			id: "grok-3-mini",
-			name: "Grok 3 Mini",
+		"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: true,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 0.5,
-				cacheRead: 0.075,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} 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"],
+			reasoning: false,
+			input: ["text", "image"],
 			cost: {
 				input: 0.2,
-				output: 1.5,
-				cacheRead: 0.02,
+				output: 0.5,
+				cacheRead: 0.05,
 				cacheWrite: 0,
 			},
-			contextWindow: 256000,
-			maxTokens: 10000,
+			contextWindow: 2000000,
+			maxTokens: 30000,
 		} satisfies Model<"openai-completions">,
-		"grok-3-mini-fast": {
-			id: "grok-3-mini-fast",
-			name: "Grok 3 Mini Fast",
+		"grok-3-fast": {
+			id: "grok-3-fast",
+			name: "Grok 3 Fast",
 			api: "openai-completions",
 			provider: "xai",
 			baseUrl: "https://api.x.ai/v1",
-			reasoning: true,
+			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.6,
-				output: 4,
-				cacheRead: 0.15,
+				input: 5,
+				output: 25,
+				cacheRead: 1.25,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -1443,6 +1426,40 @@ export const MODELS = {
 			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",
@@ -1460,6 +1477,159 @@ export const MODELS = {
 			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-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",
@@ -1477,18 +1647,18 @@ export const MODELS = {
 			contextWindow: 8192,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"grok-3-fast": {
-			id: "grok-3-fast",
-			name: "Grok 3 Fast",
+		"grok-3-mini": {
+			id: "grok-3-mini",
+			name: "Grok 3 Mini",
 			api: "openai-completions",
 			provider: "xai",
 			baseUrl: "https://api.x.ai/v1",
-			reasoning: false,
+			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 5,
-				output: 25,
-				cacheRead: 1.25,
+				input: 0.3,
+				output: 0.5,
+				cacheRead: 0.075,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -1528,26 +1698,9 @@ export const MODELS = {
 			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-mini-fast-latest": {
-			id: "grok-3-mini-fast-latest",
-			name: "Grok 3 Mini Fast Latest",
+		"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",
@@ -1562,177 +1715,24 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 8192,
 		} 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-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-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-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-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-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">,
 	},
 	zai: {
-		"glm-4.5v": {
-			id: "glm-4.5v",
-			name: "GLM 4.5V",
+		"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", "image"],
+			input: ["text"],
 			cost: {
-				input: 0.6,
-				output: 1.8,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 64000,
-			maxTokens: 16384,
+			contextWindow: 131072,
+			maxTokens: 98304,
 		} satisfies Model<"anthropic-messages">,
 		"glm-4.5": {
 			id: "glm-4.5",
@@ -1751,40 +1751,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 98304,
 		} 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-4.5-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-air": {
 			id: "glm-4.5-air",
 			name: "GLM-4.5-Air",
@@ -1802,8 +1768,59 @@ export const MODELS = {
 			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">,
 	},
 	openrouter: {
+		"openrouter/andromeda-alpha": {
+			id: "openrouter/andromeda-alpha",
+			name: "Andromeda Alpha",
+			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">,
 		"deepcogito/cogito-v2-preview-llama-405b": {
 			id: "deepcogito/cogito-v2-preview-llama-405b",
 			name: "Deep Cogito: Cogito V2 Preview Llama 405B",
@@ -1847,13 +1864,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.18,
-				output: 0.69,
+				input: 0.08,
+				output: 0.5,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 262144,
-			maxTokens: 4096,
+			contextWindow: 131072,
+			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
 		"inclusionai/ring-1t": {
 			id: "inclusionai/ring-1t",
@@ -1915,13 +1932,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.29,
+				input: 0.19999999999999998,
 				output: 1,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 262144,
-			maxTokens: 262144,
+			contextWindow: 131072,
+			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-vl-30b-a3b-instruct": {
 			id: "qwen/qwen3-vl-30b-a3b-instruct",
@@ -1932,13 +1949,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.29,
-				output: 0.9900000000000001,
+				input: 0.19999999999999998,
+				output: 0.7,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 262144,
-			maxTokens: 4096,
+			contextWindow: 131072,
+			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
 		"z-ai/glm-4.6": {
 			id: "z-ai/glm-4.6",
@@ -2005,8 +2022,8 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 4096,
+			contextWindow: 262144,
+			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-max": {
 			id: "qwen/qwen3-max",
@@ -2357,13 +2374,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.19999999999999998,
-				output: 0.7999999999999999,
+				input: 0.27,
+				output: 1,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 163840,
-			maxTokens: 163840,
+			contextWindow: 131072,
+			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
 		"mistralai/mistral-medium-3.1": {
 			id: "mistralai/mistral-medium-3.1",
@@ -2528,7 +2545,7 @@ export const MODELS = {
 			input: ["text"],
 			cost: {
 				input: 0.35,
-				output: 1.55,
+				output: 1.5,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -2561,13 +2578,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.14,
-				output: 0.86,
+				input: 0.13,
+				output: 0.85,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 131072,
+			maxTokens: 98304,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-235b-a22b-thinking-2507": {
 			id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -2804,12 +2821,12 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 32768,
+			contextWindow: 40000,
 			maxTokens: 40000,
 		} satisfies Model<"openai-completions">,
-		"mistralai/magistral-medium-2506:thinking": {
-			id: "mistralai/magistral-medium-2506:thinking",
-			name: "Mistral: Magistral Medium 2506 (thinking)",
+		"mistralai/magistral-medium-2506": {
+			id: "mistralai/magistral-medium-2506",
+			name: "Mistral: Magistral Medium 2506",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
@@ -2824,9 +2841,9 @@ export const MODELS = {
 			contextWindow: 40960,
 			maxTokens: 40000,
 		} satisfies Model<"openai-completions">,
-		"mistralai/magistral-medium-2506": {
-			id: "mistralai/magistral-medium-2506",
-			name: "Mistral: Magistral Medium 2506",
+		"mistralai/magistral-medium-2506:thinking": {
+			id: "mistralai/magistral-medium-2506:thinking",
+			name: "Mistral: Magistral Medium 2506 (thinking)",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
@@ -3059,7 +3076,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
+			contextWindow: 40960,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-235b-a22b": {
@@ -3433,8 +3450,8 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 65536,
-			maxTokens: 4096,
+			contextWindow: 131072,
+			maxTokens: 2048,
 		} satisfies Model<"openai-completions">,
 		"meta-llama/llama-3.3-70b-instruct": {
 			id: "meta-llama/llama-3.3-70b-instruct",
@@ -3518,7 +3535,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 32768,
+			contextWindow: 131072,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"mistralai/mistral-large-2407": {
@@ -3589,6 +3606,23 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"qwen/qwen-2.5-7b-instruct": {
+			id: "qwen/qwen-2.5-7b-instruct",
+			name: "Qwen: Qwen2.5 7B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.04,
+				output: 0.09999999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 16384,
+		} 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",
@@ -3674,23 +3708,6 @@ export const MODELS = {
 			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)",
@@ -3708,6 +3725,23 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4000,
 		} 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">,
 		"sao10k/l3.1-euryale-70b": {
 			id: "sao10k/l3.1-euryale-70b",
 			name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@@ -3776,6 +3810,23 @@ export const MODELS = {
 			contextWindow: 32768,
 			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: 16384,
+			maxTokens: 16384,
+		} 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",
@@ -3793,23 +3844,6 @@ export const MODELS = {
 			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">,
 		"mistralai/mistral-nemo": {
 			id: "mistralai/mistral-nemo",
 			name: "Mistral: Mistral Nemo",
@@ -3844,23 +3878,6 @@ export const MODELS = {
 			contextWindow: 8192,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-7b-instruct-v0.3": {
-			id: "mistralai/mistral-7b-instruct-v0.3",
-			name: "Mistral: Mistral 7B Instruct v0.3",
-			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">,
 		"mistralai/mistral-7b-instruct:free": {
 			id: "mistralai/mistral-7b-instruct:free",
 			name: "Mistral: Mistral 7B Instruct (free)",
@@ -3895,6 +3912,23 @@ export const MODELS = {
 			contextWindow: 32768,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-7b-instruct-v0.3": {
+			id: "mistralai/mistral-7b-instruct-v0.3",
+			name: "Mistral: Mistral 7B Instruct v0.3",
+			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",
@@ -3929,23 +3963,6 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4096,
 		} 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",
@@ -3963,6 +3980,23 @@ export const MODELS = {
 			contextWindow: 8192,
 			maxTokens: 16384,
 		} 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">,
 		"mistralai/mixtral-8x22b-instruct": {
 			id: "mistralai/mixtral-8x22b-instruct",
 			name: "Mistral: Mixtral 8x22B Instruct",
@@ -3972,8 +4006,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.8999999999999999,
-				output: 0.8999999999999999,
+				input: 2,
+				output: 6,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -3997,23 +4031,6 @@ export const MODELS = {
 			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/mistral-small": {
 			id: "mistralai/mistral-small",
 			name: "Mistral Small",
@@ -4031,6 +4048,23 @@ export const MODELS = {
 			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-8x7b-instruct": {
 			id: "mistralai/mixtral-8x7b-instruct",
 			name: "Mistral: Mixtral 8x7B Instruct",
diff --git a/packages/web-ui/package.json b/packages/web-ui/package.json
index ea96f254..4a462be5 100644
--- a/packages/web-ui/package.json
+++ b/packages/web-ui/package.json
@@ -28,10 +28,10 @@
 		"xlsx": "^0.18.5"
 	},
 	"peerDependencies": {
-		"@mariozechner/mini-lit": "^0.1.9"
+		"@mariozechner/mini-lit": "^0.1.10"
 	},
 	"devDependencies": {
-		"@mariozechner/mini-lit": "^0.1.9",
+		"@mariozechner/mini-lit": "^0.1.10",
 		"@tailwindcss/cli": "^4.0.0-beta.14",
 		"concurrently": "^9.2.1",
 		"typescript": "^5.7.3"