mirror of
https://github.com/getcompanion-ai/co-mono.git
synced 2026-04-15 09:01:14 +00:00
Add [Unreleased] section for next cycle
This commit is contained in:
Mario Zechner
parent
2668a1125d
commit
d0543d3c18
7 changed files with 381 additions and 231 deletions
|
|
@ -1,5 +1,7 @@
|
|||
# Changelog
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [0.52.10] - 2026-02-12
|
||||
|
||||
## [0.52.9] - 2026-02-08
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
# Changelog
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [0.52.10] - 2026-02-12
|
||||
|
||||
### Added
|
||||
|
|
|
|||
|
|
@ -804,6 +804,23 @@ export const MODELS = {
|
|||
contextWindow: 204608,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"minimax.minimax-m2.1": {
|
||||
id: "minimax.minimax-m2.1",
|
||||
name: "MiniMax M2.1",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"mistral.ministral-3-14b-instruct": {
|
||||
id: "mistral.ministral-3-14b-instruct",
|
||||
name: "Ministral 14B 3.0",
|
||||
|
|
@ -906,6 +923,23 @@ export const MODELS = {
|
|||
contextWindow: 256000,
|
||||
maxTokens: 256000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"moonshotai.kimi-k2.5": {
|
||||
id: "moonshotai.kimi-k2.5",
|
||||
name: "Kimi K2.5",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 256000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"nvidia.nemotron-nano-12b-v2": {
|
||||
id: "nvidia.nemotron-nano-12b-v2",
|
||||
name: "NVIDIA Nemotron Nano 12B v2 VL BF16",
|
||||
|
|
@ -1229,6 +1263,40 @@ export const MODELS = {
|
|||
contextWindow: 200000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"zai.glm-4.7": {
|
||||
id: "zai.glm-4.7",
|
||||
name: "GLM-4.7",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 2.2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"zai.glm-4.7-flash": {
|
||||
id: "zai.glm-4.7-flash",
|
||||
name: "GLM-4.7-Flash",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.07,
|
||||
output: 0.4,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
},
|
||||
"anthropic": {
|
||||
"claude-3-5-haiku-20241022": {
|
||||
|
|
@ -2066,6 +2134,23 @@ export const MODELS = {
|
|||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"gpt-5.3-codex-spark": {
|
||||
id: "gpt-5.3-codex-spark",
|
||||
name: "GPT-5.3 Codex Spark",
|
||||
api: "azure-openai-responses",
|
||||
provider: "azure-openai-responses",
|
||||
baseUrl: "",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.75,
|
||||
output: 14,
|
||||
cacheRead: 0.175,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 32000,
|
||||
} satisfies Model<"azure-openai-responses">,
|
||||
"o1": {
|
||||
id: "o1",
|
||||
name: "o1",
|
||||
|
|
@ -2221,6 +2306,23 @@ export const MODELS = {
|
|||
contextWindow: 131072,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"llama3.1-8b": {
|
||||
id: "llama3.1-8b",
|
||||
name: "Llama 3.1 8B",
|
||||
api: "openai-completions",
|
||||
provider: "cerebras",
|
||||
baseUrl: "https://api.cerebras.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.1,
|
||||
output: 0.1,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 32000,
|
||||
maxTokens: 8000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen-3-235b-a22b-instruct-2507": {
|
||||
id: "qwen-3-235b-a22b-instruct-2507",
|
||||
name: "Qwen 3 235B Instruct",
|
||||
|
|
@ -2273,7 +2375,7 @@ export const MODELS = {
|
|||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16000,
|
||||
maxTokens: 32000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"claude-opus-4.5": {
|
||||
id: "claude-opus-4.5",
|
||||
|
|
@ -2291,7 +2393,7 @@ export const MODELS = {
|
|||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16000,
|
||||
maxTokens: 32000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"claude-opus-4.6": {
|
||||
id: "claude-opus-4.6",
|
||||
|
|
@ -2345,7 +2447,7 @@ export const MODELS = {
|
|||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16000,
|
||||
maxTokens: 32000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"gemini-2.5-pro": {
|
||||
id: "gemini-2.5-pro",
|
||||
|
|
@ -2420,7 +2522,7 @@ export const MODELS = {
|
|||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
contextWindow: 64000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"gpt-4o": {
|
||||
|
|
@ -2494,7 +2596,7 @@ export const MODELS = {
|
|||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 128000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"openai-responses">,
|
||||
"gpt-5.1-codex": {
|
||||
id: "gpt-5.1-codex",
|
||||
|
|
@ -2548,7 +2650,7 @@ export const MODELS = {
|
|||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 100000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-responses">,
|
||||
"gpt-5.2": {
|
||||
id: "gpt-5.2",
|
||||
|
|
@ -3872,6 +3974,24 @@ export const MODELS = {
|
|||
contextWindow: 200000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"zai-org/GLM-5": {
|
||||
id: "zai-org/GLM-5",
|
||||
name: "GLM-5",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1,
|
||||
output: 3.2,
|
||||
cacheRead: 0.2,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 202752,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
},
|
||||
"kimi-coding": {
|
||||
"k2p5": {
|
||||
|
|
@ -4868,6 +4988,23 @@ export const MODELS = {
|
|||
contextWindow: 400000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-responses">,
|
||||
"gpt-5.3-codex-spark": {
|
||||
id: "gpt-5.3-codex-spark",
|
||||
name: "GPT-5.3 Codex Spark",
|
||||
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: 32000,
|
||||
} satisfies Model<"openai-responses">,
|
||||
"o1": {
|
||||
id: "o1",
|
||||
name: "o1",
|
||||
|
|
@ -5108,6 +5245,23 @@ export const MODELS = {
|
|||
contextWindow: 272000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-codex-responses">,
|
||||
"gpt-5.3-codex-spark": {
|
||||
id: "gpt-5.3-codex-spark",
|
||||
name: "GPT-5.3 Codex Spark",
|
||||
api: "openai-codex-responses",
|
||||
provider: "openai-codex",
|
||||
baseUrl: "https://chatgpt.com/backend-api",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-codex-responses">,
|
||||
},
|
||||
"opencode": {
|
||||
"big-pickle": {
|
||||
|
|
@ -5314,23 +5468,6 @@ export const MODELS = {
|
|||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"glm-4.7-free": {
|
||||
id: "glm-4.7-free",
|
||||
name: "GLM-4.7 Free",
|
||||
api: "openai-completions",
|
||||
provider: "opencode",
|
||||
baseUrl: "https://opencode.ai/zen/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"gpt-5": {
|
||||
id: "gpt-5",
|
||||
name: "GPT-5",
|
||||
|
|
@ -5569,12 +5706,12 @@ export const MODELS = {
|
|||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"minimax-m2.1-free": {
|
||||
id: "minimax-m2.1-free",
|
||||
name: "MiniMax M2.1 Free",
|
||||
api: "anthropic-messages",
|
||||
"minimax-m2.5-free": {
|
||||
id: "minimax-m2.5-free",
|
||||
name: "MiniMax M2.5 Free",
|
||||
api: "openai-completions",
|
||||
provider: "opencode",
|
||||
baseUrl: "https://opencode.ai/zen",
|
||||
baseUrl: "https://opencode.ai/zen/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
|
|
@ -5585,40 +5722,6 @@ export const MODELS = {
|
|||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"qwen3-coder": {
|
||||
id: "qwen3-coder",
|
||||
name: "Qwen3 Coder",
|
||||
api: "openai-completions",
|
||||
provider: "opencode",
|
||||
baseUrl: "https://opencode.ai/zen/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.45,
|
||||
output: 1.8,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"trinity-large-preview-free": {
|
||||
id: "trinity-large-preview-free",
|
||||
name: "Trinity Large Preview",
|
||||
api: "openai-completions",
|
||||
provider: "opencode",
|
||||
baseUrl: "https://opencode.ai/zen/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
},
|
||||
"openrouter": {
|
||||
|
|
@ -5639,23 +5742,6 @@ export const MODELS = {
|
|||
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",
|
||||
|
|
@ -6778,6 +6864,23 @@ export const MODELS = {
|
|||
contextWindow: 196608,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"minimax/minimax-m2.5": {
|
||||
id: "minimax/minimax-m2.5",
|
||||
name: "MiniMax: MiniMax M2.5",
|
||||
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,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/codestral-2508": {
|
||||
id: "mistralai/codestral-2508",
|
||||
name: "Mistral: Codestral 2508",
|
||||
|
|
@ -6863,23 +6966,6 @@ 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",
|
||||
|
|
@ -6897,23 +6983,6 @@ export const MODELS = {
|
|||
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",
|
||||
|
|
@ -7152,23 +7221,6 @@ 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-8x22b-instruct": {
|
||||
id: "mistralai/mixtral-8x22b-instruct",
|
||||
name: "Mistral: Mixtral 8x22B Instruct",
|
||||
|
|
@ -7203,23 +7255,6 @@ export const MODELS = {
|
|||
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",
|
||||
|
|
@ -7331,9 +7366,9 @@ export const MODELS = {
|
|||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.5,
|
||||
cacheRead: 0.049999999999999996,
|
||||
input: 0.44999999999999996,
|
||||
output: 2.25,
|
||||
cacheRead: 0.070000002,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
|
|
@ -8359,6 +8394,23 @@ export const MODELS = {
|
|||
contextWindow: 200000,
|
||||
maxTokens: 100000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openrouter/aurora-alpha": {
|
||||
id: "openrouter/aurora-alpha",
|
||||
name: "Aurora Alpha",
|
||||
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: 50000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openrouter/auto": {
|
||||
id: "openrouter/auto",
|
||||
name: "Auto Router",
|
||||
|
|
@ -8393,23 +8445,6 @@ export const MODELS = {
|
|||
contextWindow: 200000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openrouter/pony-alpha": {
|
||||
id: "openrouter/pony-alpha",
|
||||
name: "Pony Alpha",
|
||||
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: 200000,
|
||||
maxTokens: 131000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"prime-intellect/intellect-3": {
|
||||
id: "prime-intellect/intellect-3",
|
||||
name: "Prime Intellect: INTELLECT-3",
|
||||
|
|
@ -8472,7 +8507,7 @@ export const MODELS = {
|
|||
cost: {
|
||||
input: 1.5999999999999999,
|
||||
output: 6.3999999999999995,
|
||||
cacheRead: 0.64,
|
||||
cacheRead: 0.32,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 32768,
|
||||
|
|
@ -8489,11 +8524,11 @@ export const MODELS = {
|
|||
cost: {
|
||||
input: 0.39999999999999997,
|
||||
output: 1.2,
|
||||
cacheRead: 0.16,
|
||||
cacheRead: 0.08,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 8192,
|
||||
contextWindow: 1000000,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen-plus-2025-07-28": {
|
||||
id: "qwen/qwen-plus-2025-07-28",
|
||||
|
|
@ -8522,7 +8557,7 @@ export const MODELS = {
|
|||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.39999999999999997,
|
||||
output: 4,
|
||||
output: 1.2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
|
|
@ -8540,10 +8575,10 @@ export const MODELS = {
|
|||
cost: {
|
||||
input: 0.049999999999999996,
|
||||
output: 0.19999999999999998,
|
||||
cacheRead: 0.02,
|
||||
cacheRead: 0.01,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1000000,
|
||||
contextWindow: 131072,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen-vl-max": {
|
||||
|
|
@ -8561,7 +8596,7 @@ export const MODELS = {
|
|||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 8192,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-14b": {
|
||||
id: "qwen/qwen3-14b",
|
||||
|
|
@ -8589,13 +8624,13 @@ export const MODELS = {
|
|||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.19999999999999998,
|
||||
output: 0.6,
|
||||
cacheRead: 0,
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0.15,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 40960,
|
||||
maxTokens: 4096,
|
||||
maxTokens: 40960,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-235b-a22b-2507": {
|
||||
id: "qwen/qwen3-235b-a22b-2507",
|
||||
|
|
@ -8739,7 +8774,7 @@ export const MODELS = {
|
|||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: true,
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.22,
|
||||
|
|
@ -8778,10 +8813,10 @@ export const MODELS = {
|
|||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.5,
|
||||
cacheRead: 0.08,
|
||||
cacheRead: 0.06,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
contextWindow: 1000000,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-coder-next": {
|
||||
|
|
@ -8812,10 +8847,10 @@ export const MODELS = {
|
|||
cost: {
|
||||
input: 1,
|
||||
output: 5,
|
||||
cacheRead: 0.09999999999999999,
|
||||
cacheRead: 0.19999999999999998,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
contextWindow: 1000000,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-coder:exacto": {
|
||||
|
|
@ -8866,8 +8901,25 @@ export const MODELS = {
|
|||
cacheRead: 0.24,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 32768,
|
||||
contextWindow: 262144,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-max-thinking": {
|
||||
id: "qwen/qwen3-max-thinking",
|
||||
name: "Qwen: Qwen3 Max Thinking",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1.2,
|
||||
output: 6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-next-80b-a3b-instruct": {
|
||||
id: "qwen/qwen3-next-80b-a3b-instruct",
|
||||
|
|
@ -8946,13 +8998,13 @@ export const MODELS = {
|
|||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.44999999999999996,
|
||||
output: 3.5,
|
||||
input: 0,
|
||||
output: 0,
|
||||
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",
|
||||
|
|
@ -8963,13 +9015,13 @@ export const MODELS = {
|
|||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.6,
|
||||
cacheRead: 0.075,
|
||||
input: 0.13,
|
||||
output: 0.52,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 4096,
|
||||
contextWindow: 131072,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-vl-30b-a3b-thinking": {
|
||||
id: "qwen/qwen3-vl-30b-a3b-thinking",
|
||||
|
|
@ -8980,8 +9032,25 @@ export const MODELS = {
|
|||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.19999999999999998,
|
||||
output: 1,
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwen3-vl-32b-instruct": {
|
||||
id: "qwen/qwen3-vl-32b-instruct",
|
||||
name: "Qwen: Qwen3 VL 32B Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.10400000000000001,
|
||||
output: 0.41600000000000004,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
|
|
@ -9014,12 +9083,12 @@ export const MODELS = {
|
|||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.18,
|
||||
output: 2.0999999999999996,
|
||||
input: 0.117,
|
||||
output: 1.365,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
contextWindow: 131072,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen/qwq-32b": {
|
||||
|
|
@ -9090,22 +9159,22 @@ export const MODELS = {
|
|||
contextWindow: 32768,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"stepfun-ai/step3": {
|
||||
id: "stepfun-ai/step3",
|
||||
name: "StepFun: Step3",
|
||||
"stepfun/step-3.5-flash": {
|
||||
id: "stepfun/step-3.5-flash",
|
||||
name: "StepFun: Step 3.5 Flash",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.5700000000000001,
|
||||
output: 1.42,
|
||||
cacheRead: 0,
|
||||
input: 0.09999999999999999,
|
||||
output: 0.3,
|
||||
cacheRead: 0.02,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 65536,
|
||||
maxTokens: 65536,
|
||||
contextWindow: 256000,
|
||||
maxTokens: 256000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"stepfun/step-3.5-flash:free": {
|
||||
id: "stepfun/step-3.5-flash:free",
|
||||
|
|
@ -9381,7 +9450,7 @@ export const MODELS = {
|
|||
} satisfies Model<"openai-completions">,
|
||||
"z-ai/glm-4-32b": {
|
||||
id: "z-ai/glm-4-32b",
|
||||
name: "Z.AI: GLM 4 32B ",
|
||||
name: "Z.ai: GLM 4 32B ",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
|
|
@ -9398,7 +9467,7 @@ export const MODELS = {
|
|||
} satisfies Model<"openai-completions">,
|
||||
"z-ai/glm-4.5": {
|
||||
id: "z-ai/glm-4.5",
|
||||
name: "Z.AI: GLM 4.5",
|
||||
name: "Z.ai: GLM 4.5",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
|
|
@ -9415,7 +9484,7 @@ export const MODELS = {
|
|||
} satisfies Model<"openai-completions">,
|
||||
"z-ai/glm-4.5-air": {
|
||||
id: "z-ai/glm-4.5-air",
|
||||
name: "Z.AI: GLM 4.5 Air",
|
||||
name: "Z.ai: GLM 4.5 Air",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
|
|
@ -9432,7 +9501,7 @@ export const MODELS = {
|
|||
} 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)",
|
||||
name: "Z.ai: GLM 4.5 Air (free)",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
|
|
@ -9449,7 +9518,7 @@ export const MODELS = {
|
|||
} satisfies Model<"openai-completions">,
|
||||
"z-ai/glm-4.5v": {
|
||||
id: "z-ai/glm-4.5v",
|
||||
name: "Z.AI: GLM 4.5V",
|
||||
name: "Z.ai: GLM 4.5V",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
|
|
@ -9466,7 +9535,7 @@ export const MODELS = {
|
|||
} satisfies Model<"openai-completions">,
|
||||
"z-ai/glm-4.6": {
|
||||
id: "z-ai/glm-4.6",
|
||||
name: "Z.AI: GLM 4.6",
|
||||
name: "Z.ai: GLM 4.6",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
|
|
@ -9483,7 +9552,7 @@ export const MODELS = {
|
|||
} satisfies Model<"openai-completions">,
|
||||
"z-ai/glm-4.6:exacto": {
|
||||
id: "z-ai/glm-4.6:exacto",
|
||||
name: "Z.AI: GLM 4.6 (exacto)",
|
||||
name: "Z.ai: GLM 4.6 (exacto)",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
|
|
@ -9500,7 +9569,7 @@ export const MODELS = {
|
|||
} satisfies Model<"openai-completions">,
|
||||
"z-ai/glm-4.6v": {
|
||||
id: "z-ai/glm-4.6v",
|
||||
name: "Z.AI: GLM 4.6V",
|
||||
name: "Z.ai: GLM 4.6V",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
|
|
@ -9517,7 +9586,7 @@ export const MODELS = {
|
|||
} satisfies Model<"openai-completions">,
|
||||
"z-ai/glm-4.7": {
|
||||
id: "z-ai/glm-4.7",
|
||||
name: "Z.AI: GLM 4.7",
|
||||
name: "Z.ai: GLM 4.7",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
|
|
@ -9534,7 +9603,7 @@ export const MODELS = {
|
|||
} satisfies Model<"openai-completions">,
|
||||
"z-ai/glm-4.7-flash": {
|
||||
id: "z-ai/glm-4.7-flash",
|
||||
name: "Z.AI: GLM 4.7 Flash",
|
||||
name: "Z.ai: GLM 4.7 Flash",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
|
|
@ -9549,6 +9618,23 @@ export const MODELS = {
|
|||
contextWindow: 202752,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"z-ai/glm-5": {
|
||||
id: "z-ai/glm-5",
|
||||
name: "Z.ai: GLM 5",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.7999999999999999,
|
||||
output: 2.56,
|
||||
cacheRead: 0.16,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 202752,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
},
|
||||
"vercel-ai-gateway": {
|
||||
"alibaba/qwen-3-14b": {
|
||||
|
|
@ -10036,8 +10122,8 @@ export const MODELS = {
|
|||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1,
|
||||
input: 0.21,
|
||||
output: 0.7899999999999999,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
|
|
@ -10061,22 +10147,22 @@ export const MODELS = {
|
|||
contextWindow: 131072,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"deepseek/deepseek-v3.2-exp": {
|
||||
id: "deepseek/deepseek-v3.2-exp",
|
||||
name: "DeepSeek V3.2 Exp",
|
||||
"deepseek/deepseek-v3.2": {
|
||||
id: "deepseek/deepseek-v3.2",
|
||||
name: "DeepSeek V3.2",
|
||||
api: "anthropic-messages",
|
||||
provider: "vercel-ai-gateway",
|
||||
baseUrl: "https://ai-gateway.vercel.sh",
|
||||
reasoning: true,
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.27,
|
||||
output: 0.39999999999999997,
|
||||
cacheRead: 0,
|
||||
input: 0.26,
|
||||
output: 0.38,
|
||||
cacheRead: 0.13,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 163840,
|
||||
maxTokens: 163840,
|
||||
contextWindow: 128000,
|
||||
maxTokens: 8000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"deepseek/deepseek-v3.2-thinking": {
|
||||
id: "deepseek/deepseek-v3.2-thinking",
|
||||
|
|
@ -10435,6 +10521,23 @@ export const MODELS = {
|
|||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"minimax/minimax-m2.5": {
|
||||
id: "minimax/minimax-m2.5",
|
||||
name: "MiniMax M2.5",
|
||||
api: "anthropic-messages",
|
||||
provider: "vercel-ai-gateway",
|
||||
baseUrl: "https://ai-gateway.vercel.sh",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0.03,
|
||||
cacheWrite: 0.375,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"mistral/codestral": {
|
||||
id: "mistral/codestral",
|
||||
name: "Mistral Codestral",
|
||||
|
|
@ -10956,7 +11059,7 @@ export const MODELS = {
|
|||
cost: {
|
||||
input: 1.25,
|
||||
output: 10,
|
||||
cacheRead: 0.125,
|
||||
cacheRead: 0.13,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 400000,
|
||||
|
|
@ -11676,6 +11779,23 @@ export const MODELS = {
|
|||
contextWindow: 200000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"zai/glm-5": {
|
||||
id: "zai/glm-5",
|
||||
name: "GLM-5",
|
||||
api: "anthropic-messages",
|
||||
provider: "vercel-ai-gateway",
|
||||
baseUrl: "https://ai-gateway.vercel.sh",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1,
|
||||
output: 3.1999999999999997,
|
||||
cacheRead: 0.19999999999999998,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 202800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
},
|
||||
"xai": {
|
||||
"grok-2": {
|
||||
|
|
@ -12198,5 +12318,23 @@ export const MODELS = {
|
|||
contextWindow: 200000,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"glm-5": {
|
||||
id: "glm-5",
|
||||
name: "GLM-5",
|
||||
api: "openai-completions",
|
||||
provider: "zai",
|
||||
baseUrl: "https://api.z.ai/api/coding/paas/v4",
|
||||
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai"},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1,
|
||||
output: 3.2,
|
||||
cacheRead: 0.2,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
},
|
||||
} as const;
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
# Changelog
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [0.52.10] - 2026-02-12
|
||||
|
||||
### New Features
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
# Changelog
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [0.52.10] - 2026-02-12
|
||||
|
||||
## [0.52.9] - 2026-02-08
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
# Changelog
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [0.52.10] - 2026-02-12
|
||||
|
||||
### Added
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
# Changelog
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [0.52.10] - 2026-02-12
|
||||
|
||||
### Fixed
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue