mirror of
https://github.com/getcompanion-ai/co-mono.git
synced 2026-04-18 15:03:02 +00:00
feat(ai): add Hugging Face provider support
- Add huggingface to KnownProvider type - Add HF_TOKEN env var mapping - Process huggingface models from models.dev (14 models) - Use openai-completions API with compat settings - Add tests for all provider test suites - Update documentation fixes #994
This commit is contained in:
Mario Zechner
parent
f3cfb7e1ae
commit
c808de605a
16 changed files with 562 additions and 23 deletions
|
|
@ -3282,6 +3282,260 @@ export const MODELS = {
|
|||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
},
|
||||
"huggingface": {
|
||||
"MiniMaxAI/MiniMax-M2.1": {
|
||||
id: "MiniMaxAI/MiniMax-M2.1",
|
||||
name: "MiniMax-M2.1",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"Qwen/Qwen3-235B-A22B-Thinking-2507": {
|
||||
id: "Qwen/Qwen3-235B-A22B-Thinking-2507",
|
||||
name: "Qwen3-235B-A22B-Thinking-2507",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"Qwen/Qwen3-Coder-480B-A35B-Instruct": {
|
||||
id: "Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
||||
name: "Qwen3-Coder-480B-A35B-Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 2,
|
||||
output: 2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 66536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"Qwen/Qwen3-Next-80B-A3B-Instruct": {
|
||||
id: "Qwen/Qwen3-Next-80B-A3B-Instruct",
|
||||
name: "Qwen3-Next-80B-A3B-Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.25,
|
||||
output: 1,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 66536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"Qwen/Qwen3-Next-80B-A3B-Thinking": {
|
||||
id: "Qwen/Qwen3-Next-80B-A3B-Thinking",
|
||||
name: "Qwen3-Next-80B-A3B-Thinking",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"XiaomiMiMo/MiMo-V2-Flash": {
|
||||
id: "XiaomiMiMo/MiMo-V2-Flash",
|
||||
name: "MiMo-V2-Flash",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.1,
|
||||
output: 0.3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"deepseek-ai/DeepSeek-R1-0528": {
|
||||
id: "deepseek-ai/DeepSeek-R1-0528",
|
||||
name: "DeepSeek-R1-0528",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 3,
|
||||
output: 5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 163840,
|
||||
maxTokens: 163840,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"deepseek-ai/DeepSeek-V3.2": {
|
||||
id: "deepseek-ai/DeepSeek-V3.2",
|
||||
name: "DeepSeek-V3.2",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.28,
|
||||
output: 0.4,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 163840,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"moonshotai/Kimi-K2-Instruct": {
|
||||
id: "moonshotai/Kimi-K2-Instruct",
|
||||
name: "Kimi-K2-Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
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: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1,
|
||||
output: 3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"moonshotai/Kimi-K2-Thinking": {
|
||||
id: "moonshotai/Kimi-K2-Thinking",
|
||||
name: "Kimi-K2-Thinking",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 2.5,
|
||||
cacheRead: 0.15,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"moonshotai/Kimi-K2.5": {
|
||||
id: "moonshotai/Kimi-K2.5",
|
||||
name: "Kimi-K2.5",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 3,
|
||||
cacheRead: 0.1,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"zai-org/GLM-4.7": {
|
||||
id: "zai-org/GLM-4.7",
|
||||
name: "GLM-4.7",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 2.2,
|
||||
cacheRead: 0.11,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"zai-org/GLM-4.7-Flash": {
|
||||
id: "zai-org/GLM-4.7-Flash",
|
||||
name: "GLM-4.7-Flash",
|
||||
api: "openai-completions",
|
||||
provider: "huggingface",
|
||||
baseUrl: "https://router.huggingface.co/v1",
|
||||
compat: {"supportsDeveloperRole":false},
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
},
|
||||
"minimax": {
|
||||
"MiniMax-M2": {
|
||||
id: "MiniMax-M2",
|
||||
|
|
@ -4823,6 +5077,40 @@ export const MODELS = {
|
|||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"kimi-k2.5": {
|
||||
id: "kimi-k2.5",
|
||||
name: "Kimi K2.5",
|
||||
api: "openai-completions",
|
||||
provider: "opencode",
|
||||
baseUrl: "https://opencode.ai/zen/v1",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 3,
|
||||
cacheRead: 0.1,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"minimax-m2.1": {
|
||||
id: "minimax-m2.1",
|
||||
name: "MiniMax M2.1",
|
||||
api: "openai-completions",
|
||||
provider: "opencode",
|
||||
baseUrl: "https://opencode.ai/zen/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0.1,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen3-coder": {
|
||||
id: "qwen3-coder",
|
||||
name: "Qwen3 Coder",
|
||||
|
|
@ -5182,6 +5470,23 @@ export const MODELS = {
|
|||
contextWindow: 1000000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"arcee-ai/trinity-large-preview:free": {
|
||||
id: "arcee-ai/trinity-large-preview:free",
|
||||
name: "Arcee AI: Trinity Large Preview (free)",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"arcee-ai/trinity-mini": {
|
||||
id: "arcee-ai/trinity-mini",
|
||||
name: "Arcee AI: Trinity Mini",
|
||||
|
|
@ -5550,7 +5855,7 @@ export const MODELS = {
|
|||
cost: {
|
||||
input: 0.21,
|
||||
output: 0.32,
|
||||
cacheRead: 0,
|
||||
cacheRead: 0.21,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 163840,
|
||||
|
|
@ -5673,7 +5978,7 @@ export const MODELS = {
|
|||
cacheWrite: 0.08333333333333334,
|
||||
},
|
||||
contextWindow: 1048576,
|
||||
maxTokens: 65535,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"google/gemini-2.5-pro": {
|
||||
id: "google/gemini-2.5-pro",
|
||||
|
|
@ -6066,23 +6371,6 @@ export const MODELS = {
|
|||
contextWindow: 262144,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/devstral-2512:free": {
|
||||
id: "mistralai/devstral-2512:free",
|
||||
name: "Mistral: Devstral 2 2512 (free)",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/devstral-medium": {
|
||||
id: "mistralai/devstral-medium",
|
||||
name: "Mistral: Devstral Medium",
|
||||
|
|
@ -6593,6 +6881,23 @@ export const MODELS = {
|
|||
contextWindow: 262144,
|
||||
maxTokens: 65535,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"moonshotai/kimi-k2.5": {
|
||||
id: "moonshotai/kimi-k2.5",
|
||||
name: "MoonshotAI: Kimi K2.5",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.5700000000000001,
|
||||
output: 2.8499999999999996,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"nex-agi/deepseek-v3.1-nex-n1": {
|
||||
id: "nex-agi/deepseek-v3.1-nex-n1",
|
||||
name: "Nex AGI: DeepSeek V3.1 Nex N1",
|
||||
|
|
@ -6687,13 +6992,13 @@ export const MODELS = {
|
|||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.06,
|
||||
output: 0.24,
|
||||
input: 0.049999999999999996,
|
||||
output: 0.19999999999999998,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"nvidia/nemotron-3-nano-30b-a3b:free": {
|
||||
id: "nvidia/nemotron-3-nano-30b-a3b:free",
|
||||
|
|
@ -7947,7 +8252,7 @@ export const MODELS = {
|
|||
cost: {
|
||||
input: 0.049999999999999996,
|
||||
output: 0.25,
|
||||
cacheRead: 0,
|
||||
cacheRead: 0.049999999999999996,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 32000,
|
||||
|
|
@ -8395,6 +8700,23 @@ export const MODELS = {
|
|||
contextWindow: 163840,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"upstage/solar-pro-3:free": {
|
||||
id: "upstage/solar-pro-3:free",
|
||||
name: "Upstage: Solar Pro 3 (free)",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"x-ai/grok-3": {
|
||||
id: "x-ai/grok-3",
|
||||
name: "xAI: Grok 3",
|
||||
|
|
@ -8890,6 +9212,23 @@ export const MODELS = {
|
|||
contextWindow: 262144,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"alibaba/qwen3-max-thinking": {
|
||||
id: "alibaba/qwen3-max-thinking",
|
||||
name: "Qwen 3 Max Thinking",
|
||||
api: "anthropic-messages",
|
||||
provider: "vercel-ai-gateway",
|
||||
baseUrl: "https://ai-gateway.vercel.sh",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1.2,
|
||||
output: 6,
|
||||
cacheRead: 0.24,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 256000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"anthropic/claude-3-haiku": {
|
||||
id: "anthropic/claude-3-haiku",
|
||||
name: "Claude 3 Haiku",
|
||||
|
|
@ -9077,6 +9416,23 @@ export const MODELS = {
|
|||
contextWindow: 1000000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"arcee-ai/trinity-large-preview": {
|
||||
id: "arcee-ai/trinity-large-preview",
|
||||
name: "Trinity Large Preview",
|
||||
api: "anthropic-messages",
|
||||
provider: "vercel-ai-gateway",
|
||||
baseUrl: "https://ai-gateway.vercel.sh",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.25,
|
||||
output: 1,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131000,
|
||||
maxTokens: 131000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"bytedance/seed-1.6": {
|
||||
id: "bytedance/seed-1.6",
|
||||
name: "Seed 1.6",
|
||||
|
|
@ -9774,6 +10130,23 @@ export const MODELS = {
|
|||
contextWindow: 256000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"moonshotai/kimi-k2.5": {
|
||||
id: "moonshotai/kimi-k2.5",
|
||||
name: "Kimi K2.5",
|
||||
api: "anthropic-messages",
|
||||
provider: "vercel-ai-gateway",
|
||||
baseUrl: "https://ai-gateway.vercel.sh",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1.2,
|
||||
output: 1.2,
|
||||
cacheRead: 0.6,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 256000,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"nvidia/nemotron-nano-12b-v2-vl": {
|
||||
id: "nvidia/nemotron-nano-12b-v2-vl",
|
||||
name: "Nvidia Nemotron Nano 12B V2 VL",
|
||||
|
|
@ -11298,5 +11671,23 @@ export const MODELS = {
|
|||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"glm-4.7-flash": {
|
||||
id: "glm-4.7-flash",
|
||||
name: "GLM-4.7-Flash",
|
||||
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: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
},
|
||||
} as const;
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue