ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
1f0dbc008c9b3e88017d42e8a1b46d416ad2b6b6
pi_harness/packages/ai/src/providers/nvidia.models.ts
T
Vegard Stikbakke ee24a9ec54 feat(ai): refresh generated model catalogs 
closes #6256
2026-07-04 06:27:58 +02:00

388 lines
13 KiB
TypeScript
Raw Blame History

// This file is auto-generated by scripts/generate-models.ts
// Do not edit manually - run 'npm run generate-models' to update
import type { Model } from "../types.ts";
export const NVIDIA_MODELS = {
"meta/llama-3.1-70b-instruct": {
id: "meta/llama-3.1-70b-instruct",
name: "Llama 3.1 70b Instruct",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"meta/llama-3.1-8b-instruct": {
id: "meta/llama-3.1-8b-instruct",
name: "Llama 3.1 8B Instruct",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 16000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"meta/llama-3.2-11b-vision-instruct": {
id: "meta/llama-3.2-11b-vision-instruct",
name: "Llama 3.2 11b Vision Instruct",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"meta/llama-3.2-90b-vision-instruct": {
id: "meta/llama-3.2-90b-vision-instruct",
name: "Llama-3.2-90B-Vision-Instruct",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"meta/llama-3.3-70b-instruct": {
id: "meta/llama-3.3-70b-instruct",
name: "Llama 3.3 70b Instruct",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"minimaxai/minimax-m3": {
id: "minimaxai/minimax-m3",
name: "MiniMax-M3",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"mistralai/mistral-large-3-675b-instruct-2512": {
id: "mistralai/mistral-large-3-675b-instruct-2512",
name: "Mistral Large 3 675B Instruct 2512",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"mistralai/mistral-small-4-119b-2603": {
id: "mistralai/mistral-small-4-119b-2603",
name: "mistral-small-4-119b-2603",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.6": {
id: "moonshotai/kimi-k2.6",
name: "Kimi K2.6",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-nano-30b-a3b": {
id: "nvidia/nemotron-3-nano-30b-a3b",
name: "nemotron-3-nano-30b-a3b",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
name: "Nemotron 3 Nano Omni",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-super-120b-a12b": {
id: "nvidia/nemotron-3-super-120b-a12b",
name: "Nemotron 3 Super",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0.2,
output: 0.8,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-ultra-550b-a55b": {
id: "nvidia/nemotron-3-ultra-550b-a55b",
name: "Nemotron 3 Ultra 550B A55B",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0.5,
output: 2.5,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"nvidia/nvidia-nemotron-nano-9b-v2": {
id: "nvidia/nvidia-nemotron-nano-9b-v2",
name: "nvidia-nemotron-nano-9b-v2",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-120b": {
id: "openai/gpt-oss-120b",
name: "GPT-OSS-120B",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-20b": {
id: "openai/gpt-oss-20b",
name: "GPT OSS 20B",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-122b-a10b": {
id: "qwen/qwen3.5-122b-a10b",
name: "Qwen3.5 122B-A10B",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"stepfun-ai/step-3.5-flash": {
id: "stepfun-ai/step-3.5-flash",
name: "Step 3.5 Flash",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"stepfun-ai/step-3.7-flash": {
id: "stepfun-ai/step-3.7-flash",
name: "Step 3.7 Flash",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.2": {
id: "z-ai/glm-5.2",
name: "GLM-5.2",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
} as const;
Reference in New Issue View Git Blame Copy Permalink