@code-yeongyu/senpi-ai 2026.10.4 → 2026.10.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/index.d.ts +1 -0
- package/dist/index.js +1 -0
- package/dist/model.d.ts +16 -0
- package/dist/model.js +10 -1
- package/dist/providers/data/.manifest.json +1 -1
- package/dist/providers/data/nvidia.json +1 -1
- package/dist/providers/data/openrouter.json +1 -1
- package/dist/utils/overflow.d.ts +3 -0
- package/dist/utils/overflow.js +15 -1
- package/dist/utils/retry-hint.d.ts +1 -1
- package/dist/utils/retry-hint.js +5 -1
- package/dist/utils/tool-choice-fallback.d.ts +10 -0
- package/dist/utils/tool-choice-fallback.js +40 -1
- package/package.json +2 -2
package/dist/index.d.ts
CHANGED
|
@@ -33,6 +33,7 @@ export { type CursorResolvedSelection, renderCursorCliModelString, resolveCursor
|
|
|
33
33
|
export * from "./endpoint-reasoning-efforts.ts";
|
|
34
34
|
export * from "./env-api-keys.ts";
|
|
35
35
|
export * from "./legacy-provider-ids.ts";
|
|
36
|
+
export { modelSupportsAssistantPrefill } from "./model.ts";
|
|
36
37
|
export * from "./models.ts";
|
|
37
38
|
export * from "./models-store.ts";
|
|
38
39
|
export { supportsAllowedToolChoice } from "./openai-responses-compat.ts";
|
package/dist/index.js
CHANGED
|
@@ -19,6 +19,7 @@ export { renderCursorCliModelString, resolveCursorSelectionDescriptor, } from ".
|
|
|
19
19
|
export * from "./endpoint-reasoning-efforts.js";
|
|
20
20
|
export * from "./env-api-keys.js";
|
|
21
21
|
export * from "./legacy-provider-ids.js";
|
|
22
|
+
export { modelSupportsAssistantPrefill } from "./model.js";
|
|
22
23
|
export * from "./models.js";
|
|
23
24
|
export * from "./models-store.js";
|
|
24
25
|
export { supportsAllowedToolChoice } from "./openai-responses-compat.js";
|
package/dist/model.d.ts
CHANGED
|
@@ -36,6 +36,14 @@ export interface Model<TApi extends Api> extends BaseModel<TApi> {
|
|
|
36
36
|
serviceTier?: "auto" | "flex" | "priority" | "ultrafast";
|
|
37
37
|
/** Whether to recover supported text-encoded tool calls from assistant text. */
|
|
38
38
|
recoverTextToolCalls?: boolean;
|
|
39
|
+
/**
|
|
40
|
+
* Whether a request may end with an assistant message the model continues
|
|
41
|
+
* writing (assistant prefill). Absent means no: Claude 4.6 and later reject a
|
|
42
|
+
* trailing assistant message, OpenAI's Responses API has no prefill, and the
|
|
43
|
+
* other default providers document none. Set it per model only after a live
|
|
44
|
+
* probe; `modelSupportsAssistantPrefill` also applies the request settings.
|
|
45
|
+
*/
|
|
46
|
+
supportsAssistantPrefill?: boolean;
|
|
39
47
|
/** Compatibility overrides for OpenAI-compatible APIs. If not set, auto-detected from baseUrl. */
|
|
40
48
|
compat?: TApi extends "openai-completions" ? OpenAICompletionsCompat : TApi extends "openai-responses" | "openai-codex-responses" | "azure-openai-responses" ? OpenAIResponsesCompat : TApi extends "anthropic-messages" ? AnthropicMessagesCompat : TApi extends "bedrock-converse-stream" ? BedrockCompat : TApi extends "mistral-conversations" ? MistralConversationsCompat : TApi extends "cursor-agent" ? CursorAgentCompat : TApi extends "devin-agent" ? DevinAgentCompat : never;
|
|
41
49
|
}
|
|
@@ -75,4 +83,12 @@ export interface CursorAgentCompat {
|
|
|
75
83
|
variantIds?: Readonly<Partial<Record<ModelThinkingLevel, string>>>;
|
|
76
84
|
};
|
|
77
85
|
}
|
|
86
|
+
/**
|
|
87
|
+
* Whether a request to `model` with these settings may end with an assistant
|
|
88
|
+
* message the model continues writing. Extended thinking rules prefill out on
|
|
89
|
+
* the Anthropic Messages API even for models that otherwise accept it.
|
|
90
|
+
*/
|
|
91
|
+
export declare function modelSupportsAssistantPrefill(model: Pick<Model<Api>, "api" | "supportsAssistantPrefill">, settings: {
|
|
92
|
+
readonly thinkingEnabled: boolean;
|
|
93
|
+
}): boolean;
|
|
78
94
|
//# sourceMappingURL=model.d.ts.map
|
package/dist/model.js
CHANGED
|
@@ -1,2 +1,11 @@
|
|
|
1
|
-
|
|
1
|
+
/**
|
|
2
|
+
* Whether a request to `model` with these settings may end with an assistant
|
|
3
|
+
* message the model continues writing. Extended thinking rules prefill out on
|
|
4
|
+
* the Anthropic Messages API even for models that otherwise accept it.
|
|
5
|
+
*/
|
|
6
|
+
export function modelSupportsAssistantPrefill(model, settings) {
|
|
7
|
+
if (model.supportsAssistantPrefill !== true)
|
|
8
|
+
return false;
|
|
9
|
+
return !(model.api === "anthropic-messages" && settings.thinkingEnabled);
|
|
10
|
+
}
|
|
2
11
|
//# sourceMappingURL=model.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"schemaVersion":6,"generatedAt":"2026-10-
|
|
1
|
+
{"schemaVersion":6,"generatedAt":"2026-10-04T02:15:25.826Z","structureHash":"5bcf793c5cb2e77e2e7db5984d35392c5e7257735e503113a1062d2211c93ee4","files":{"alibaba-token-plan.json":"16b3c6c78d72c73ca34a1e79ce71c0cf36ba409d02e83a17396ce0949a1d5363","amazon-bedrock.json":"657f75bb65b8a3bc07019f2f2e71e5d0e01f5da49756d24ee9b2f3d06f1fb4c0","ant-ling.json":"628feab3ef6c7d80ce96f75999804e1d9f05fec3851e5302e30fff3b69db90f6","anthropic.json":"2c0c4389cd71d21d4553075f399922892078192b0490fead423544e360af1a43","azure-openai-responses.json":"a3e52bd78f0220aa32bce519e13955b8e6e567860416343844cbe19902f4a682","bai.json":"7e6861aaf27d8af34e1771c6092602194fcec0a0046e6adfab9c3ee54d32b99f","baseten.json":"b04d1423d6958bec857ffccc36726f091ec1a8f3a09cf0836b64cc94b0ee697d","cerebras.json":"3eccb58c5de3d0dc7ba49dc6e477ba29f00cb3150ce0a35cc90d59e6b5ab368e","chatgpt-subscription.json":"08f365952647594f5b07337666255f8510ef2e09bfb704530843b63121ed07f4","cloudflare-ai-gateway.json":"2ba4b7f1b0ba8919760c2e9cbd994270edd179bc9d291f271eede738afcbf269","cloudflare-workers-ai.json":"4bf0b488460c2e6cb8a6615bb2f87ca2a31cd9597eb249d5b58cba251330a99a","deepseek.json":"10a296fb3e898f7715c80890c8af0af4f5fd58f22dbcd6612fdc5d762157ccdc","fireworks.json":"c3dc21dc2e95428fc9a38e3840c05bbf90f94e4c25dee0eedf0b385b49ff65a4","github-copilot.json":"9ed67e5c0104ec237e9befcb9a50a18bd7d65e1539cd9f0638d2bc20bd82ef60","google-vertex.json":"40090c680538bc867f2624d986a449f361be4dfa6ba96d7a27402050f036e009","google.json":"c0f5a633e5e5a5044432db3e537f4bc674d4de18df09325c6349547fcc13cabe","groq.json":"910952ad9dad07856983459d63fce0148dba1203edd7b10d801a77c5824f3405","huggingface.json":"1b8604bd31a5e05fe43a40ec1ec6dfc1a51a28b0b020151ef057fab43f57c923","meta.json":"0c7e9a370a7005c5a89dc94f0f93bc67b8935c3f802de324f11af6ff56fff429","minimax-cn.json":"f962c20ee6a6a342820f778e9dc363a18a524bf11998f6e2c57f2989915d62e5","minimax.json":"17a432f80d0ea6dd26eade80a4314250d3a855678601728a5f70dd8fa0d21dd2","mistral.json":"10f33bff9adf1248f7e6848e5890c265399f1f94e5b42cfdc28c109d547af98d","moonshotai-cn.json":"bfb0641eee9587118da525607d86e55840de13310cd934785bc3bdcfeb6f88e3","moonshotai.json":"79ac5b6861a10d592e884c05a546fdd0b58fe383ce3453ecdb32d43926cba9dd","nvidia.json":"a75e963dc81779e3eec01c051b12277c15ec37c5b94ab51ece9e9ccb3b16407c","openai.json":"9104538118053eed57f90852332b6ad274a4e4792389bdbc9cfca1ae400c705a","opencode-go.json":"82e416a53efa53fed4c4e3dc0ed837fe2a0d53f110528f65af843e6fa08599e5","opencode.json":"ae373c624a66b824f543ef76fb5f1849b4910390952e6ae18b13bdb3e2d63b37","opengateway.json":"1dbdfeffa3047a941d257b9ea01c7eca2b7d794256f749a9b53c77b99247eb35","openrouter.json":"1670216010fff653d34bd070f4c2108858d0804a2e4aa73a60a9da1a4faafbc1","qwen-token-plan-cn.json":"bd36a6d9cc2048deafacc85f7f0f2e51868c8b7aa09502e3e4e60e3e8b76f690","qwen-token-plan-individual.json":"35ffb0ba1a1ce3f68fc73262dd5e07fbcb5bf5911ad1e6e17bc0621e2894676a","qwen-token-plan.json":"ca27e49e62965221badead8e867b2007035c6b6a15a97c47219bd23d2c83c2b1","radius.json":"a8cf2f2cc7dae90d8bbfdd8a2f8a0e058e7923dbdb3ba2cdaed7dd1aecd25a2a","together.json":"bbd7fad86cacfefe3d3d61f6638f22e9b6f5d575722fd1112a16aafe0485c46d","typesafe.json":"a4429a2f696d5cc5273969af61a7310bda07d6bdcd27bf9ac9c76c534cc43716","venice.json":"a5f06e8297561de8cfcce397f9609a804ec912af007ba7fdbdb1951f2ee97009","vercel-ai-gateway.json":"aa1eabd3ec0d8d7a0e783cd514c085b465a28503515cea6477f4880349d63f5c","xai.json":"d7771a1450b21c1f6aee887ca6fea61b6e7b3fc13b4dee5cf72a71134fe623bc","xiaomi-token-plan-ams.json":"4dd8f838e21d7aa7caf3122d0b0b1e5a02a33bc012b96e6a75bd119334152d7a","xiaomi-token-plan-cn.json":"46414ff49973b95a0c14bd33e8992cc1938a50ce2c7cea9e2e5cc02de8f1df31","xiaomi-token-plan-sgp.json":"f5b3f66bf7bb7238592d4a9667cad983a008d7539a66e9896b02422622800935","xiaomi.json":"8b62c158d55d5a165f35cd72c1fc82ab89ff8e73f08960105fc41b822f236f69","zai-coding-cn.json":"2a7f59d15f588a97d218997883f2506dfc52d3ee320697d39f14213a050fc912","zai.json":"e9cc408e1756de8abc70148d63d89d11a63c65b7ef06ad0661cd1328e4209ba3"}}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"openai-completions":{"chat:deepseek-ai/deepseek-v4.1-flash":{"id":"deepseek-ai/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},"contextWindow":1000000,"maxTokens":384000,"thinkingLevelMap":{"minimal":null,"low":null,"medium":null,"high":"high","max":"max"},"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/diffusiongemma-26b-a4b-it":{"id":"google/diffusiongemma-26b-a4b-it","name":"DiffusionGemma 26B A4B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":250000,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/gemma-3-12b-it":{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/gemma-3-4b-it":{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat: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"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":4096,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat: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"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":8192,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:meta/muse-glimmer-30b":{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:mistralai/mistral-7b-instruct-v0.3":{"id":"mistralai/mistral-7b-instruct-v0.3","name":"Mistral-7B-Instruct-v0.3","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":65536,"maxTokens":65536,"type":"chat"},"chat: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"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1048576,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/cosmos-reason2-8b":{"id":"nvidia/cosmos-reason2-8b","name":"Cosmos Reason2 8B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/llama-3.1-nemotron-70b-instruct":{"id":"nvidia/llama-3.1-nemotron-70b-instruct","name":"Llama 3.1 Nemotron 70B Instruct","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":8192,"type":"chat"},"chat:nvidia/llama-3.1-nemotron-ultra-253b-v1":{"id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","name":"Llama 3.1 Nemotron Ultra 253B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":16384,"type":"chat"},"chat: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"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":256000,"maxTokens":65536,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat: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"},"reasoning":true,"input":["text"],"cost":{"input":0.5,"output":2.5,"cacheRead":0.15,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1000000,"maxTokens":65536,"type":"chat"},"chat:nvidia/nemotron-3.5-lightning-30b-a3b":{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":262144,"type":"chat"},"chat: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"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":32768,"type":"chat"},"chat:poolside/laguna-xs-2.1":{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":16384,"type":"chat"},"chat:z-ai/glm-5.3":{"id":"z-ai/glm-5.3","name":"GLM-5.3","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1000000,"maxTokens":131072,"type":"chat"},"chat:z-ai/glm-5.3-flash":{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1000000,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"}}}
|
|
1
|
+
{"openai-completions":{"chat:deepseek-ai/deepseek-v4.1-flash":{"id":"deepseek-ai/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},"contextWindow":1000000,"maxTokens":384000,"thinkingLevelMap":{"minimal":null,"low":null,"medium":null,"high":"high","max":"max"},"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/diffusiongemma-26b-a4b-it":{"id":"google/diffusiongemma-26b-a4b-it","name":"DiffusionGemma 26B A4B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":250000,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/gemma-3-12b-it":{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/gemma-3-4b-it":{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat: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"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":4096,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat: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"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":8192,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:meta/muse-glimmer-30b":{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:mistralai/mistral-7b-instruct-v0.3":{"id":"mistralai/mistral-7b-instruct-v0.3","name":"Mistral-7B-Instruct-v0.3","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":65536,"maxTokens":65536,"type":"chat"},"chat: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"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1048576,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/cosmos-reason2-8b":{"id":"nvidia/cosmos-reason2-8b","name":"Cosmos Reason2 8B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/llama-3.1-nemotron-70b-instruct":{"id":"nvidia/llama-3.1-nemotron-70b-instruct","name":"Llama 3.1 Nemotron 70B Instruct","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":8192,"type":"chat"},"chat:nvidia/llama-3.1-nemotron-ultra-253b-v1":{"id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","name":"Llama 3.1 Nemotron Ultra 253B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":16384,"type":"chat"},"chat: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"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":256000,"maxTokens":65536,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat: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"},"reasoning":true,"input":["text"],"cost":{"input":0.2,"output":0.8,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":262144,"type":"chat"},"chat: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"},"reasoning":true,"input":["text"],"cost":{"input":0.5,"output":2.5,"cacheRead":0.15,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1000000,"maxTokens":65536,"type":"chat"},"chat:nvidia/nemotron-3.5-lightning-30b-a3b":{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":262144,"type":"chat"},"chat: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"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":32768,"type":"chat"},"chat:poolside/laguna-xs-2.1":{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":16384,"type":"chat"},"chat:z-ai/glm-5.3":{"id":"z-ai/glm-5.3","name":"GLM-5.3","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1000000,"maxTokens":131072,"type":"chat"},"chat:z-ai/glm-5.3-flash":{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1000000,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"}}}
|