@tanstack/ai-vercel-gateway 0.0.1 → 0.1.1

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.
Files changed (5) hide show
  1. package/dist/esm/model-meta.d.ts +69 -13
  2. package/dist/esm/model-meta.js +25 -1
  3. package/dist/esm/model-meta.js.map +1 -1
  4. package/package.json +6 -6
  5. package/src/model-meta.ts +279 -21
package/dist/esm/model-meta.d.ts CHANGED
@@ -1,11 +1,11 @@
1
1
  import { VercelGatewayEmbeddingProviderOptions } from './embedding/embedding-provider-options.js';
2
2
  import { VercelGatewayImageProviderOptions, VercelGatewayImageSize } from './image/image-provider-options.js';
3
3
  import { VercelGatewayBaseOptions, VercelGatewayCommonOptions, VercelGatewayTextProviderOptions } from './text/text-provider-options.js';
4
- export declare const VERCEL_GATEWAY_CHAT_MODELS: readonly ["alibaba/qwen-3-14b", "alibaba/qwen-3-235b", "alibaba/qwen-3-30b", "alibaba/qwen-3-32b", "alibaba/qwen-3.6-max-preview", "alibaba/qwen3-235b-a22b-thinking", "alibaba/qwen3-coder", "alibaba/qwen3-coder-30b-a3b", "alibaba/qwen3-coder-next", "alibaba/qwen3-coder-plus", "alibaba/qwen3-max", "alibaba/qwen3-max-preview", "alibaba/qwen3-max-thinking", "alibaba/qwen3-next-80b-a3b-instruct", "alibaba/qwen3-next-80b-a3b-thinking", "alibaba/qwen3-vl-235b-a22b-instruct", "alibaba/qwen3-vl-instruct", "alibaba/qwen3-vl-thinking", "alibaba/qwen3.5-flash", "alibaba/qwen3.5-plus", "alibaba/qwen3.6-27b", "alibaba/qwen3.6-plus", "alibaba/qwen3.7-flash", "alibaba/qwen3.7-max", "alibaba/qwen3.7-plus", "alibaba/qwen3.8-max", "amazon/nova-2-lite", "amazon/nova-lite", "amazon/nova-micro", "amazon/nova-pro", "anthropic/claude-3-haiku", "anthropic/claude-fable-5", "anthropic/claude-haiku-4.5", "anthropic/claude-opus-4", "anthropic/claude-opus-4.5", "anthropic/claude-opus-4.6", "anthropic/claude-opus-4.7", "anthropic/claude-opus-4.8", "anthropic/claude-opus-4.8-fast", "anthropic/claude-opus-5", "anthropic/claude-opus-5-fast", "anthropic/claude-sonnet-4", "anthropic/claude-sonnet-4.5", "anthropic/claude-sonnet-4.6", "anthropic/claude-sonnet-5", "arcee-ai/trinity-large-thinking", "arcee-ai/trinity-mini", "bytedance/seed-1.6", "bytedance/seed-1.8", "cohere/command-a", "deepseek/deepseek-r1", "deepseek/deepseek-v3", "deepseek/deepseek-v3.1", "deepseek/deepseek-v3.1-terminus", "deepseek/deepseek-v3.2", "deepseek/deepseek-v3.2-thinking", "deepseek/deepseek-v4-flash", "deepseek/deepseek-v4-flash-0731", "deepseek/deepseek-v4-pro", "fish-audio/s1", "fish-audio/s2-pro", "fish-audio/s2.1-pro", "fish-audio/transcribe-1", "google/gemini-2.5-flash", "google/gemini-2.5-flash-image", "google/gemini-2.5-flash-lite", "google/gemini-2.5-pro", "google/gemini-3-flash", "google/gemini-3-pro-image", "google/gemini-3.1-flash-image", "google/gemini-3.1-flash-image-preview", "google/gemini-3.1-flash-lite", "google/gemini-3.1-flash-lite-image", "google/gemini-3.1-pro-preview", "google/gemini-3.5-flash", "google/gemini-3.5-flash-lite", "google/gemini-3.6-flash", "google/gemini-omni-flash-preview", "google/gemma-4-26b-a4b-it", "google/gemma-4-31b-it", "inception/mercury-2", "inception/mercury-coder-small", "inclusionai/ling-3.0-flash", "inclusionai/ling-3.0-tiny-free", "interfaze/interfaze-beta", "kwaipilot/kat-coder-air-v2.5", "kwaipilot/kat-coder-pro-v1", "kwaipilot/kat-coder-pro-v2", "kwaipilot/kat-coder-pro-v2.5", "meta/llama-3.1-70b", "meta/llama-3.1-8b", "meta/llama-3.3-70b", "meta/llama-4-maverick", "meta/llama-4-scout", "meta/muse-glimmer-30b", "meta/muse-spark-1.1", "meta/muse-spark-1.2", "meta/muse-spark-1.2-contributor", "minimax/minimax-m2", "minimax/minimax-m2.1", "minimax/minimax-m2.1-lightning", "minimax/minimax-m2.5", "minimax/minimax-m2.5-highspeed", "minimax/minimax-m2.7", "minimax/minimax-m2.7-highspeed", "minimax/minimax-m3", "mistral/codestral", "mistral/devstral-2", "mistral/devstral-small-2", "mistral/magistral-medium", "mistral/magistral-small", "mistral/ministral-14b", "mistral/ministral-3b", "mistral/ministral-8b", "mistral/mistral-large-3", "mistral/mistral-medium", "mistral/mistral-medium-3.5", "mistral/mistral-nemo", "mistral/mistral-small", "mistral/pixtral-12b", "moonshotai/kimi-k2", "moonshotai/kimi-k2-thinking", "moonshotai/kimi-k2.5", "moonshotai/kimi-k2.6", "moonshotai/kimi-k2.7-code", "moonshotai/kimi-k2.7-code-highspeed", "moonshotai/kimi-k3", "moonshotai/kimi-k3-fast", "morph/morph-v3-fast", "morph/morph-v3-large", "nvidia/nemotron-3-nano-30b-a3b", "nvidia/nemotron-3-super-120b-a12b", "nvidia/nemotron-3-ultra-550b-a55b", "nvidia/nemotron-nano-12b-v2-vl", "nvidia/nemotron-nano-9b-v2", "openai/gpt-3.5-turbo", "openai/gpt-4-turbo", "openai/gpt-4.1", "openai/gpt-4.1-mini", "openai/gpt-4.1-nano", "openai/gpt-4o", "openai/gpt-4o-mini", "openai/gpt-4o-mini-search-preview", "openai/gpt-4o-mini-transcribe", "openai/gpt-4o-transcribe", "openai/gpt-5", "openai/gpt-5-codex", "openai/gpt-5-mini", "openai/gpt-5-nano", "openai/gpt-5-pro", "openai/gpt-5.1-codex", "openai/gpt-5.1-codex-max", "openai/gpt-5.1-codex-mini", "openai/gpt-5.1-thinking", "openai/gpt-5.2", "openai/gpt-5.2-codex", "openai/gpt-5.2-pro", "openai/gpt-5.3-codex", "openai/gpt-5.4", "openai/gpt-5.4-mini", "openai/gpt-5.4-nano", "openai/gpt-5.4-pro", "openai/gpt-5.5", "openai/gpt-5.5-pro", "openai/gpt-5.6-luna", "openai/gpt-5.6-sol", "openai/gpt-5.6-terra", "openai/gpt-oss-120b", "openai/gpt-oss-20b", "openai/gpt-oss-safeguard-20b", "openai/gpt-realtime-1.5", "openai/gpt-realtime-2", "openai/gpt-realtime-2.1", "openai/gpt-realtime-mini", "openai/gpt-realtime-whisper", "openai/o1", "openai/o3", "openai/o3-deep-research", "openai/o3-mini", "openai/o3-pro", "openai/o4-mini", "openai/tts-1", "openai/tts-1-hd", "openai/whisper-1", "perplexity/sonar", "perplexity/sonar-pro", "perplexity/sonar-reasoning-pro", "poolside/laguna-s-2.1", "poolside/laguna-s-2.1-free", "sakana/fugu-ultra", "sakana/namazu", "stepfun/step-3.5-flash", "stepfun/step-3.7-flash", "tencent/hy3", "thinkingmachines/inkling", "thinkingmachines/inkling-small", "xai/grok-4.1-fast-non-reasoning", "xai/grok-4.1-fast-reasoning", "xai/grok-4.20-multi-agent", "xai/grok-4.20-multi-agent-beta", "xai/grok-4.20-non-reasoning", "xai/grok-4.20-non-reasoning-beta", "xai/grok-4.20-reasoning", "xai/grok-4.20-reasoning-beta", "xai/grok-4.3", "xai/grok-4.5", "xai/grok-build-0.1", "xai/grok-stt", "xai/grok-tts", "xai/grok-voice-think-fast-1.0", "xai/grok-voice-think-fast-2.0", "xiaomi/mimo-v2.5", "xiaomi/mimo-v2.5-pro", "zai/glm-4.5", "zai/glm-4.5-air", "zai/glm-4.5v", "zai/glm-4.6", "zai/glm-4.6v", "zai/glm-4.6v-flash", "zai/glm-4.7", "zai/glm-4.7-flash", "zai/glm-4.7-flashx", "zai/glm-5", "zai/glm-5-turbo", "zai/glm-5.1", "zai/glm-5.2", "zai/glm-5.2-fast", "zai/glm-5v-turbo"];
4
+ export declare const VERCEL_GATEWAY_CHAT_MODELS: readonly ["alibaba/qwen-3-14b", "alibaba/qwen-3-235b", "alibaba/qwen-3-30b", "alibaba/qwen-3-32b", "alibaba/qwen-3.6-max-preview", "alibaba/qwen3-235b-a22b-thinking", "alibaba/qwen3-coder", "alibaba/qwen3-coder-30b-a3b", "alibaba/qwen3-coder-next", "alibaba/qwen3-coder-plus", "alibaba/qwen3-max", "alibaba/qwen3-max-preview", "alibaba/qwen3-max-thinking", "alibaba/qwen3-next-80b-a3b-instruct", "alibaba/qwen3-next-80b-a3b-thinking", "alibaba/qwen3-vl-235b-a22b-instruct", "alibaba/qwen3-vl-instruct", "alibaba/qwen3-vl-thinking", "alibaba/qwen3.5-flash", "alibaba/qwen3.5-plus", "alibaba/qwen3.6-27b", "alibaba/qwen3.6-plus", "alibaba/qwen3.7-flash", "alibaba/qwen3.7-max", "alibaba/qwen3.7-plus", "alibaba/qwen3.8-2.4t-a95b", "alibaba/qwen3.8-27b", "alibaba/qwen3.8-max", "amazon/nova-2-lite", "amazon/nova-lite", "amazon/nova-micro", "amazon/nova-pro", "anthropic/claude-3-haiku", "anthropic/claude-fable-5", "anthropic/claude-haiku-4.5", "anthropic/claude-opus-4", "anthropic/claude-opus-4.5", "anthropic/claude-opus-4.6", "anthropic/claude-opus-4.7", "anthropic/claude-opus-4.8", "anthropic/claude-opus-4.8-fast", "anthropic/claude-opus-5", "anthropic/claude-opus-5-fast", "anthropic/claude-sonnet-4", "anthropic/claude-sonnet-4.5", "anthropic/claude-sonnet-4.6", "anthropic/claude-sonnet-5", "arcee-ai/trinity-large-thinking", "arcee-ai/trinity-mini", "bytedance/seed-1.6", "bytedance/seed-1.8", "cohere/command-a", "deepseek/deepseek-r1", "deepseek/deepseek-v3", "deepseek/deepseek-v3.1", "deepseek/deepseek-v3.1-terminus", "deepseek/deepseek-v3.2", "deepseek/deepseek-v3.2-thinking", "deepseek/deepseek-v4-flash", "deepseek/deepseek-v4-flash-0731", "deepseek/deepseek-v4-pro", "deepseek/deepseek-v4-pro-0813", "fish-audio/s1", "fish-audio/s2-pro", "fish-audio/s2.1-pro", "fish-audio/transcribe-1", "google/gemini-2.5-flash", "google/gemini-2.5-flash-image", "google/gemini-2.5-flash-lite", "google/gemini-2.5-pro", "google/gemini-3-flash", "google/gemini-3-pro-image", "google/gemini-3.1-flash-image", "google/gemini-3.1-flash-image-preview", "google/gemini-3.1-flash-lite", "google/gemini-3.1-flash-lite-image", "google/gemini-3.1-pro-preview", "google/gemini-3.5-flash", "google/gemini-3.5-flash-lite", "google/gemini-3.6-flash", "google/gemini-3.7-flash", "google/gemini-omni-flash-preview", "google/gemma-4-26b-a4b-it", "google/gemma-4-31b-it", "inception/mercury-2", "inception/mercury-coder-small", "inclusionai/ling-3.0-flash", "interfaze/interfaze-beta", "kwaipilot/kat-coder-air-v2.5", "kwaipilot/kat-coder-pro-v1", "kwaipilot/kat-coder-pro-v2", "kwaipilot/kat-coder-pro-v2.5", "meta/llama-3.1-70b", "meta/llama-3.1-8b", "meta/llama-3.3-70b", "meta/llama-4-maverick", "meta/llama-4-scout", "meta/muse-glimmer-30b", "meta/muse-spark-1.1", "meta/muse-spark-1.2", "meta/muse-spark-1.2-contributor", "minimax/minimax-m2", "minimax/minimax-m2.1", "minimax/minimax-m2.1-lightning", "minimax/minimax-m2.5", "minimax/minimax-m2.5-highspeed", "minimax/minimax-m2.7", "minimax/minimax-m2.7-highspeed", "minimax/minimax-m3", "mistral/codestral", "mistral/devstral-2", "mistral/devstral-small-2", "mistral/magistral-medium", "mistral/magistral-small", "mistral/ministral-14b", "mistral/ministral-3b", "mistral/ministral-8b", "mistral/mistral-large-3", "mistral/mistral-medium", "mistral/mistral-medium-3.5", "mistral/mistral-nemo", "mistral/mistral-small", "mistral/pixtral-12b", "moonshotai/kimi-k2", "moonshotai/kimi-k2-thinking", "moonshotai/kimi-k2.5", "moonshotai/kimi-k2.6", "moonshotai/kimi-k2.7-code", "moonshotai/kimi-k2.7-code-highspeed", "moonshotai/kimi-k3", "moonshotai/kimi-k3-fast", "morph/morph-v3-fast", "morph/morph-v3-large", "nvidia/nemotron-3-nano-30b-a3b", "nvidia/nemotron-3-super-120b-a12b", "nvidia/nemotron-3-ultra-550b-a55b", "nvidia/nemotron-3.5-lightning", "nvidia/nemotron-nano-12b-v2-vl", "nvidia/nemotron-nano-9b-v2", "openai/gpt-3.5-turbo", "openai/gpt-4-turbo", "openai/gpt-4.1", "openai/gpt-4.1-fast", "openai/gpt-4.1-mini", "openai/gpt-4.1-mini-fast", "openai/gpt-4.1-nano", "openai/gpt-4.1-nano-fast", "openai/gpt-4o", "openai/gpt-4o-fast", "openai/gpt-4o-mini", "openai/gpt-4o-mini-fast", "openai/gpt-4o-mini-search-preview", "openai/gpt-4o-mini-transcribe", "openai/gpt-4o-transcribe", "openai/gpt-5", "openai/gpt-5-codex", "openai/gpt-5-fast", "openai/gpt-5-mini", "openai/gpt-5-mini-fast", "openai/gpt-5-nano", "openai/gpt-5-pro", "openai/gpt-5.1-codex", "openai/gpt-5.1-codex-max", "openai/gpt-5.1-codex-mini", "openai/gpt-5.1-thinking", "openai/gpt-5.1-thinking-fast", "openai/gpt-5.2", "openai/gpt-5.2-codex", "openai/gpt-5.2-fast", "openai/gpt-5.2-pro", "openai/gpt-5.3-codex", "openai/gpt-5.3-codex-fast", "openai/gpt-5.4", "openai/gpt-5.4-fast", "openai/gpt-5.4-mini", "openai/gpt-5.4-mini-fast", "openai/gpt-5.4-nano", "openai/gpt-5.4-pro", "openai/gpt-5.5", "openai/gpt-5.5-fast", "openai/gpt-5.5-pro", "openai/gpt-5.6-luna", "openai/gpt-5.6-luna-fast", "openai/gpt-5.6-sol", "openai/gpt-5.6-sol-fast", "openai/gpt-5.6-terra", "openai/gpt-5.6-terra-fast", "openai/gpt-oss-120b", "openai/gpt-oss-20b", "openai/gpt-oss-safeguard-20b", "openai/gpt-realtime-1.5", "openai/gpt-realtime-2", "openai/gpt-realtime-2.1", "openai/gpt-realtime-mini", "openai/gpt-realtime-whisper", "openai/o1", "openai/o3", "openai/o3-deep-research", "openai/o3-fast", "openai/o3-mini", "openai/o3-pro", "openai/o4-mini", "openai/o4-mini-fast", "openai/tts-1", "openai/tts-1-hd", "openai/whisper-1", "perplexity/sonar", "perplexity/sonar-pro", "perplexity/sonar-reasoning-pro", "poolside/laguna-s-2.1", "poolside/laguna-s-2.1-free", "sakana/fugu-ultra", "sakana/namazu", "stepfun/step-3.5-flash", "stepfun/step-3.7-flash", "tencent/hy3", "thinkingmachines/inkling", "thinkingmachines/inkling-small", "xai/grok-4.1-fast-non-reasoning", "xai/grok-4.1-fast-reasoning", "xai/grok-4.20-multi-agent", "xai/grok-4.20-multi-agent-beta", "xai/grok-4.20-non-reasoning", "xai/grok-4.20-non-reasoning-beta", "xai/grok-4.20-reasoning", "xai/grok-4.20-reasoning-beta", "xai/grok-4.3", "xai/grok-4.5", "xai/grok-4.6", "xai/grok-build-0.1", "xai/grok-stt", "xai/grok-tts", "xai/grok-voice-think-fast-1.0", "xai/grok-voice-think-fast-2.0", "xiaomi/mimo-v2.5", "xiaomi/mimo-v2.5-pro", "zai/glm-4.5", "zai/glm-4.5-air", "zai/glm-4.5v", "zai/glm-4.6", "zai/glm-4.6v", "zai/glm-4.6v-flash", "zai/glm-4.7", "zai/glm-4.7-flash", "zai/glm-4.7-flashx", "zai/glm-5", "zai/glm-5-turbo", "zai/glm-5.1", "zai/glm-5.2", "zai/glm-5.2-fast", "zai/glm-5v-turbo"];
5
5
  export type VercelGatewayChatModel = (typeof VERCEL_GATEWAY_CHAT_MODELS)[number];
6
6
  export declare const VERCEL_GATEWAY_PROVIDERS: readonly ["alibaba", "amazon", "anthropic", "arcee-ai", "bfl", "bytedance", "cohere", "deepseek", "fish-audio", "google", "inception", "inclusionai", "interfaze", "klingai", "kwaipilot", "meta", "minimax", "mistral", "moonshotai", "morph", "nvidia", "openai", "perplexity", "poolside", "prodia", "quiverai", "recraft", "sakana", "stepfun", "tencent", "thinkingmachines", "voyage", "xai", "xiaomi", "zai"];
7
7
  export type VercelGatewayProvider = (typeof VERCEL_GATEWAY_PROVIDERS)[number];
8
- export declare const VERCEL_GATEWAY_MODEL_TAGS: readonly ["explicit-caching", "fast", "file-input", "free", "image-generation", "implicit-caching", "reasoning", "structured-output", "tool-use", "video-generation", "vision", "web-search", "websocket-realtime", "websocket-transcription"];
8
+ export declare const VERCEL_GATEWAY_MODEL_TAGS: readonly ["explicit-caching", "fast", "file-input", "free", "image-generation", "implicit-caching", "reasoning", "structured-output", "tool-use", "video-generation", "video-input", "vision", "web-search", "websocket-realtime", "websocket-transcription"];
9
9
  export type VercelGatewayModelTag = (typeof VERCEL_GATEWAY_MODEL_TAGS)[number];
10
10
  export declare const VERCEL_GATEWAY_EMBEDDING_MODELS: readonly ["alibaba/qwen3-embedding-0.6b", "alibaba/qwen3-embedding-4b", "alibaba/qwen3-embedding-8b", "amazon/titan-embed-text-v2", "cohere/embed-v4.0", "google/gemini-embedding-001", "google/gemini-embedding-2", "google/text-embedding-005", "google/text-multilingual-embedding-002", "mistral/codestral-embed", "mistral/mistral-embed", "openai/text-embedding-3-large", "openai/text-embedding-3-small", "openai/text-embedding-ada-002", "perplexity/pplx-embed-v1-0.6b", "perplexity/pplx-embed-v1-4b", "voyage/voyage-3-large", "voyage/voyage-3.5", "voyage/voyage-3.5-lite", "voyage/voyage-4", "voyage/voyage-4-large", "voyage/voyage-4-lite", "voyage/voyage-code-2", "voyage/voyage-code-3", "voyage/voyage-finance-2", "voyage/voyage-law-2"];
11
11
  export type VercelGatewayEmbeddingModel = (typeof VERCEL_GATEWAY_EMBEDDING_MODELS)[number];
@@ -37,6 +37,8 @@ export type VercelGatewayChatModelProviderOptionsByName = {
37
37
  'alibaba/qwen3.7-flash': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
38
38
  'alibaba/qwen3.7-max': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
39
39
  'alibaba/qwen3.7-plus': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
40
+ 'alibaba/qwen3.8-2.4t-a95b': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
41
+ 'alibaba/qwen3.8-27b': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
40
42
  'alibaba/qwen3.8-max': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
41
43
  'amazon/nova-2-lite': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
42
44
  'amazon/nova-lite': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
@@ -71,6 +73,7 @@ export type VercelGatewayChatModelProviderOptionsByName = {
71
73
  'deepseek/deepseek-v4-flash': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
72
74
  'deepseek/deepseek-v4-flash-0731': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
73
75
  'deepseek/deepseek-v4-pro': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
76
+ 'deepseek/deepseek-v4-pro-0813': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
74
77
  'fish-audio/s1': VercelGatewayCommonOptions;
75
78
  'fish-audio/s2-pro': VercelGatewayCommonOptions;
76
79
  'fish-audio/s2.1-pro': VercelGatewayCommonOptions;
@@ -89,13 +92,13 @@ export type VercelGatewayChatModelProviderOptionsByName = {
89
92
  'google/gemini-3.5-flash': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
90
93
  'google/gemini-3.5-flash-lite': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
91
94
  'google/gemini-3.6-flash': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
95
+ 'google/gemini-3.7-flash': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
92
96
  'google/gemini-omni-flash-preview': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
93
97
  'google/gemma-4-26b-a4b-it': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
94
98
  'google/gemma-4-31b-it': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
95
99
  'inception/mercury-2': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
96
100
  'inception/mercury-coder-small': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
97
101
  'inclusionai/ling-3.0-flash': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
98
- 'inclusionai/ling-3.0-tiny-free': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
99
102
  'interfaze/interfaze-beta': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
100
103
  'kwaipilot/kat-coder-air-v2.5': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
101
104
  'kwaipilot/kat-coder-pro-v1': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
@@ -145,40 +148,57 @@ export type VercelGatewayChatModelProviderOptionsByName = {
145
148
  'nvidia/nemotron-3-nano-30b-a3b': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
146
149
  'nvidia/nemotron-3-super-120b-a12b': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
147
150
  'nvidia/nemotron-3-ultra-550b-a55b': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
151
+ 'nvidia/nemotron-3.5-lightning': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
148
152
  'nvidia/nemotron-nano-12b-v2-vl': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
149
153
  'nvidia/nemotron-nano-9b-v2': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
150
154
  'openai/gpt-3.5-turbo': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
151
155
  'openai/gpt-4-turbo': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
152
156
  'openai/gpt-4.1': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
157
+ 'openai/gpt-4.1-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
153
158
  'openai/gpt-4.1-mini': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
159
+ 'openai/gpt-4.1-mini-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
154
160
  'openai/gpt-4.1-nano': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
161
+ 'openai/gpt-4.1-nano-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
155
162
  'openai/gpt-4o': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
163
+ 'openai/gpt-4o-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
156
164
  'openai/gpt-4o-mini': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
165
+ 'openai/gpt-4o-mini-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
157
166
  'openai/gpt-4o-mini-search-preview': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop'>;
158
167
  'openai/gpt-4o-mini-transcribe': VercelGatewayCommonOptions;
159
168
  'openai/gpt-4o-transcribe': VercelGatewayCommonOptions;
160
169
  'openai/gpt-5': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
161
170
  'openai/gpt-5-codex': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
171
+ 'openai/gpt-5-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
162
172
  'openai/gpt-5-mini': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
173
+ 'openai/gpt-5-mini-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
163
174
  'openai/gpt-5-nano': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
164
175
  'openai/gpt-5-pro': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
165
176
  'openai/gpt-5.1-codex': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
166
177
  'openai/gpt-5.1-codex-max': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
167
178
  'openai/gpt-5.1-codex-mini': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
168
179
  'openai/gpt-5.1-thinking': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
180
+ 'openai/gpt-5.1-thinking-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
169
181
  'openai/gpt-5.2': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
170
182
  'openai/gpt-5.2-codex': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
183
+ 'openai/gpt-5.2-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
171
184
  'openai/gpt-5.2-pro': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
172
185
  'openai/gpt-5.3-codex': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
186
+ 'openai/gpt-5.3-codex-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
173
187
  'openai/gpt-5.4': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
188
+ 'openai/gpt-5.4-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
174
189
  'openai/gpt-5.4-mini': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
190
+ 'openai/gpt-5.4-mini-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
175
191
  'openai/gpt-5.4-nano': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
176
192
  'openai/gpt-5.4-pro': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
177
193
  'openai/gpt-5.5': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
194
+ 'openai/gpt-5.5-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
178
195
  'openai/gpt-5.5-pro': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
179
196
  'openai/gpt-5.6-luna': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
197
+ 'openai/gpt-5.6-luna-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
180
198
  'openai/gpt-5.6-sol': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
199
+ 'openai/gpt-5.6-sol-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
181
200
  'openai/gpt-5.6-terra': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
201
+ 'openai/gpt-5.6-terra-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
182
202
  'openai/gpt-oss-120b': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
183
203
  'openai/gpt-oss-20b': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
184
204
  'openai/gpt-oss-safeguard-20b': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
@@ -190,9 +210,11 @@ export type VercelGatewayChatModelProviderOptionsByName = {
190
210
  'openai/o1': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
191
211
  'openai/o3': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
192
212
  'openai/o3-deep-research': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
213
+ 'openai/o3-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
193
214
  'openai/o3-mini': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
194
215
  'openai/o3-pro': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
195
216
  'openai/o4-mini': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
217
+ 'openai/o4-mini-fast': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'stop' | 'reasoning' | 'include_reasoning'>;
196
218
  'openai/tts-1': VercelGatewayCommonOptions;
197
219
  'openai/tts-1-hd': VercelGatewayCommonOptions;
198
220
  'openai/whisper-1': VercelGatewayCommonOptions;
@@ -218,6 +240,7 @@ export type VercelGatewayChatModelProviderOptionsByName = {
218
240
  'xai/grok-4.20-reasoning-beta': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
219
241
  'xai/grok-4.3': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
220
242
  'xai/grok-4.5': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
243
+ 'xai/grok-4.6': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
221
244
  'xai/grok-build-0.1': VercelGatewayCommonOptions & Pick<VercelGatewayBaseOptions, 'max_tokens' | 'max_output_tokens' | 'temperature' | 'stop' | 'reasoning' | 'include_reasoning'>;
222
245
  'xai/grok-stt': VercelGatewayCommonOptions;
223
246
  'xai/grok-tts': VercelGatewayCommonOptions;
@@ -267,6 +290,8 @@ export type VercelGatewayModelInputModalitiesByName = {
267
290
  'alibaba/qwen3.7-flash': readonly ['text', 'image', 'document'];
268
291
  'alibaba/qwen3.7-max': readonly ['text'];
269
292
  'alibaba/qwen3.7-plus': readonly ['text', 'image', 'document'];
293
+ 'alibaba/qwen3.8-2.4t-a95b': readonly ['text'];
294
+ 'alibaba/qwen3.8-27b': readonly ['text', 'image'];
270
295
  'alibaba/qwen3.8-max': readonly ['text', 'image'];
271
296
  'amazon/nova-2-lite': readonly ['text', 'image', 'document'];
272
297
  'amazon/nova-lite': readonly ['text', 'image', 'document'];
@@ -301,6 +326,7 @@ export type VercelGatewayModelInputModalitiesByName = {
301
326
  'deepseek/deepseek-v4-flash': readonly ['text'];
302
327
  'deepseek/deepseek-v4-flash-0731': readonly ['text'];
303
328
  'deepseek/deepseek-v4-pro': readonly ['text'];
329
+ 'deepseek/deepseek-v4-pro-0813': readonly ['text'];
304
330
  'fish-audio/s1': readonly ['text'];
305
331
  'fish-audio/s2-pro': readonly ['text'];
306
332
  'fish-audio/s2.1-pro': readonly ['text'];
@@ -316,16 +342,21 @@ export type VercelGatewayModelInputModalitiesByName = {
316
342
  'google/gemini-3.1-flash-lite': readonly ['text', 'image', 'document'];
317
343
  'google/gemini-3.1-flash-lite-image': readonly ['text', 'image'];
318
344
  'google/gemini-3.1-pro-preview': readonly ['text', 'image', 'document'];
319
- 'google/gemini-3.5-flash': readonly ['text', 'image', 'document'];
320
- 'google/gemini-3.5-flash-lite': readonly ['text', 'image', 'document'];
321
- 'google/gemini-3.6-flash': readonly ['text', 'image', 'document'];
345
+ 'google/gemini-3.5-flash': readonly ['text', 'image', 'document', 'video'];
346
+ 'google/gemini-3.5-flash-lite': readonly [
347
+ 'text',
348
+ 'image',
349
+ 'document',
350
+ 'video'
351
+ ];
352
+ 'google/gemini-3.6-flash': readonly ['text', 'image', 'document', 'video'];
353
+ 'google/gemini-3.7-flash': readonly ['text', 'image', 'document', 'video'];
322
354
  'google/gemini-omni-flash-preview': readonly ['text', 'image', 'document'];
323
355
  'google/gemma-4-26b-a4b-it': readonly ['text', 'image', 'document'];
324
356
  'google/gemma-4-31b-it': readonly ['text', 'image', 'document'];
325
357
  'inception/mercury-2': readonly ['text'];
326
358
  'inception/mercury-coder-small': readonly ['text'];
327
359
  'inclusionai/ling-3.0-flash': readonly ['text'];
328
- 'inclusionai/ling-3.0-tiny-free': readonly ['text'];
329
360
  'interfaze/interfaze-beta': readonly ['text', 'image', 'document'];
330
361
  'kwaipilot/kat-coder-air-v2.5': readonly ['text', 'image'];
331
362
  'kwaipilot/kat-coder-pro-v1': readonly ['text'];
@@ -364,51 +395,73 @@ export type VercelGatewayModelInputModalitiesByName = {
364
395
  'mistral/pixtral-12b': readonly ['text', 'image'];
365
396
  'moonshotai/kimi-k2': readonly ['text'];
366
397
  'moonshotai/kimi-k2-thinking': readonly ['text'];
367
- 'moonshotai/kimi-k2.5': readonly ['text', 'image'];
368
- 'moonshotai/kimi-k2.6': readonly ['text', 'image'];
369
- 'moonshotai/kimi-k2.7-code': readonly ['text', 'image', 'document'];
370
- 'moonshotai/kimi-k2.7-code-highspeed': readonly ['text', 'image', 'document'];
371
- 'moonshotai/kimi-k3': readonly ['text', 'image', 'document'];
398
+ 'moonshotai/kimi-k2.5': readonly ['text', 'image', 'video'];
399
+ 'moonshotai/kimi-k2.6': readonly ['text', 'image', 'video'];
400
+ 'moonshotai/kimi-k2.7-code': readonly ['text', 'image', 'document', 'video'];
401
+ 'moonshotai/kimi-k2.7-code-highspeed': readonly [
402
+ 'text',
403
+ 'image',
404
+ 'document',
405
+ 'video'
406
+ ];
407
+ 'moonshotai/kimi-k3': readonly ['text', 'image', 'document', 'video'];
372
408
  'moonshotai/kimi-k3-fast': readonly ['text', 'image', 'document'];
373
409
  'morph/morph-v3-fast': readonly ['text'];
374
410
  'morph/morph-v3-large': readonly ['text'];
375
411
  'nvidia/nemotron-3-nano-30b-a3b': readonly ['text'];
376
412
  'nvidia/nemotron-3-super-120b-a12b': readonly ['text'];
377
413
  'nvidia/nemotron-3-ultra-550b-a55b': readonly ['text'];
414
+ 'nvidia/nemotron-3.5-lightning': readonly ['text'];
378
415
  'nvidia/nemotron-nano-12b-v2-vl': readonly ['text', 'image'];
379
416
  'nvidia/nemotron-nano-9b-v2': readonly ['text'];
380
417
  'openai/gpt-3.5-turbo': readonly ['text'];
381
418
  'openai/gpt-4-turbo': readonly ['text', 'image'];
382
419
  'openai/gpt-4.1': readonly ['text', 'image', 'document'];
420
+ 'openai/gpt-4.1-fast': readonly ['text', 'image', 'document'];
383
421
  'openai/gpt-4.1-mini': readonly ['text', 'image', 'document'];
422
+ 'openai/gpt-4.1-mini-fast': readonly ['text', 'image', 'document'];
384
423
  'openai/gpt-4.1-nano': readonly ['text', 'image', 'document'];
424
+ 'openai/gpt-4.1-nano-fast': readonly ['text', 'image', 'document'];
385
425
  'openai/gpt-4o': readonly ['text', 'image', 'document'];
426
+ 'openai/gpt-4o-fast': readonly ['text', 'image', 'document'];
386
427
  'openai/gpt-4o-mini': readonly ['text', 'image', 'document'];
428
+ 'openai/gpt-4o-mini-fast': readonly ['text', 'image', 'document'];
387
429
  'openai/gpt-4o-mini-search-preview': readonly ['text'];
388
430
  'openai/gpt-4o-mini-transcribe': readonly ['text', 'audio'];
389
431
  'openai/gpt-4o-transcribe': readonly ['text', 'audio'];
390
432
  'openai/gpt-5': readonly ['text', 'image', 'document'];
391
433
  'openai/gpt-5-codex': readonly ['text', 'image', 'document'];
434
+ 'openai/gpt-5-fast': readonly ['text', 'image', 'document'];
392
435
  'openai/gpt-5-mini': readonly ['text', 'image', 'document'];
436
+ 'openai/gpt-5-mini-fast': readonly ['text', 'image', 'document'];
393
437
  'openai/gpt-5-nano': readonly ['text', 'image', 'document'];
394
438
  'openai/gpt-5-pro': readonly ['text', 'image', 'document'];
395
439
  'openai/gpt-5.1-codex': readonly ['text', 'image', 'document'];
396
440
  'openai/gpt-5.1-codex-max': readonly ['text', 'image', 'document'];
397
441
  'openai/gpt-5.1-codex-mini': readonly ['text', 'image', 'document'];
398
442
  'openai/gpt-5.1-thinking': readonly ['text', 'image', 'document'];
443
+ 'openai/gpt-5.1-thinking-fast': readonly ['text', 'image', 'document'];
399
444
  'openai/gpt-5.2': readonly ['text', 'image', 'document'];
400
445
  'openai/gpt-5.2-codex': readonly ['text', 'image', 'document'];
446
+ 'openai/gpt-5.2-fast': readonly ['text', 'image', 'document'];
401
447
  'openai/gpt-5.2-pro': readonly ['text', 'image', 'document'];
402
448
  'openai/gpt-5.3-codex': readonly ['text', 'image', 'document'];
449
+ 'openai/gpt-5.3-codex-fast': readonly ['text', 'image', 'document'];
403
450
  'openai/gpt-5.4': readonly ['text', 'image', 'document'];
451
+ 'openai/gpt-5.4-fast': readonly ['text', 'image', 'document'];
404
452
  'openai/gpt-5.4-mini': readonly ['text', 'image', 'document'];
453
+ 'openai/gpt-5.4-mini-fast': readonly ['text', 'image', 'document'];
405
454
  'openai/gpt-5.4-nano': readonly ['text', 'image', 'document'];
406
455
  'openai/gpt-5.4-pro': readonly ['text', 'image', 'document'];
407
456
  'openai/gpt-5.5': readonly ['text', 'image', 'document'];
457
+ 'openai/gpt-5.5-fast': readonly ['text', 'image', 'document'];
408
458
  'openai/gpt-5.5-pro': readonly ['text', 'image', 'document'];
409
459
  'openai/gpt-5.6-luna': readonly ['text', 'image', 'document'];
460
+ 'openai/gpt-5.6-luna-fast': readonly ['text', 'image', 'document'];
410
461
  'openai/gpt-5.6-sol': readonly ['text', 'image', 'document'];
462
+ 'openai/gpt-5.6-sol-fast': readonly ['text', 'image', 'document'];
411
463
  'openai/gpt-5.6-terra': readonly ['text', 'image', 'document'];
464
+ 'openai/gpt-5.6-terra-fast': readonly ['text', 'image', 'document'];
412
465
  'openai/gpt-oss-120b': readonly ['text'];
413
466
  'openai/gpt-oss-20b': readonly ['text'];
414
467
  'openai/gpt-oss-safeguard-20b': readonly ['text'];
@@ -420,9 +473,11 @@ export type VercelGatewayModelInputModalitiesByName = {
420
473
  'openai/o1': readonly ['text', 'image', 'document'];
421
474
  'openai/o3': readonly ['text', 'image', 'document'];
422
475
  'openai/o3-deep-research': readonly ['text', 'image', 'document'];
476
+ 'openai/o3-fast': readonly ['text', 'image', 'document'];
423
477
  'openai/o3-mini': readonly ['text'];
424
478
  'openai/o3-pro': readonly ['text', 'image', 'document'];
425
479
  'openai/o4-mini': readonly ['text', 'image', 'document'];
480
+ 'openai/o4-mini-fast': readonly ['text', 'image', 'document'];
426
481
  'openai/tts-1': readonly ['text'];
427
482
  'openai/tts-1-hd': readonly ['text'];
428
483
  'openai/whisper-1': readonly ['text', 'audio'];
@@ -448,12 +503,13 @@ export type VercelGatewayModelInputModalitiesByName = {
448
503
  'xai/grok-4.20-reasoning-beta': readonly ['text', 'image', 'document'];
449
504
  'xai/grok-4.3': readonly ['text', 'image', 'document'];
450
505
  'xai/grok-4.5': readonly ['text', 'image', 'document'];
506
+ 'xai/grok-4.6': readonly ['text', 'image'];
451
507
  'xai/grok-build-0.1': readonly ['text', 'image'];
452
508
  'xai/grok-stt': readonly ['text', 'audio'];
453
509
  'xai/grok-tts': readonly ['text'];
454
510
  'xai/grok-voice-think-fast-1.0': readonly ['text', 'audio'];
455
511
  'xai/grok-voice-think-fast-2.0': readonly ['text', 'audio'];
456
- 'xiaomi/mimo-v2.5': readonly ['text', 'image', 'document'];
512
+ 'xiaomi/mimo-v2.5': readonly ['text', 'image'];
457
513
  'xiaomi/mimo-v2.5-pro': readonly ['text'];
458
514
  'zai/glm-4.5': readonly ['text'];
459
515
  'zai/glm-4.5-air': readonly ['text'];
package/dist/esm/model-meta.js CHANGED
@@ -25,6 +25,8 @@ var VERCEL_GATEWAY_CHAT_MODELS = [
25
25
  "alibaba/qwen3.7-flash",
26
26
  "alibaba/qwen3.7-max",
27
27
  "alibaba/qwen3.7-plus",
28
+ "alibaba/qwen3.8-2.4t-a95b",
29
+ "alibaba/qwen3.8-27b",
28
30
  "alibaba/qwen3.8-max",
29
31
  "amazon/nova-2-lite",
30
32
  "amazon/nova-lite",
@@ -59,6 +61,7 @@ var VERCEL_GATEWAY_CHAT_MODELS = [
59
61
  "deepseek/deepseek-v4-flash",
60
62
  "deepseek/deepseek-v4-flash-0731",
61
63
  "deepseek/deepseek-v4-pro",
64
+ "deepseek/deepseek-v4-pro-0813",
62
65
  "fish-audio/s1",
63
66
  "fish-audio/s2-pro",
64
67
  "fish-audio/s2.1-pro",
@@ -77,13 +80,13 @@ var VERCEL_GATEWAY_CHAT_MODELS = [
77
80
  "google/gemini-3.5-flash",
78
81
  "google/gemini-3.5-flash-lite",
79
82
  "google/gemini-3.6-flash",
83
+ "google/gemini-3.7-flash",
80
84
  "google/gemini-omni-flash-preview",
81
85
  "google/gemma-4-26b-a4b-it",
82
86
  "google/gemma-4-31b-it",
83
87
  "inception/mercury-2",
84
88
  "inception/mercury-coder-small",
85
89
  "inclusionai/ling-3.0-flash",
86
- "inclusionai/ling-3.0-tiny-free",
87
90
  "interfaze/interfaze-beta",
88
91
  "kwaipilot/kat-coder-air-v2.5",
89
92
  "kwaipilot/kat-coder-pro-v1",
@@ -133,40 +136,57 @@ var VERCEL_GATEWAY_CHAT_MODELS = [
133
136
  "nvidia/nemotron-3-nano-30b-a3b",
134
137
  "nvidia/nemotron-3-super-120b-a12b",
135
138
  "nvidia/nemotron-3-ultra-550b-a55b",
139
+ "nvidia/nemotron-3.5-lightning",
136
140
  "nvidia/nemotron-nano-12b-v2-vl",
137
141
  "nvidia/nemotron-nano-9b-v2",
138
142
  "openai/gpt-3.5-turbo",
139
143
  "openai/gpt-4-turbo",
140
144
  "openai/gpt-4.1",
145
+ "openai/gpt-4.1-fast",
141
146
  "openai/gpt-4.1-mini",
147
+ "openai/gpt-4.1-mini-fast",
142
148
  "openai/gpt-4.1-nano",
149
+ "openai/gpt-4.1-nano-fast",
143
150
  "openai/gpt-4o",
151
+ "openai/gpt-4o-fast",
144
152
  "openai/gpt-4o-mini",
153
+ "openai/gpt-4o-mini-fast",
145
154
  "openai/gpt-4o-mini-search-preview",
146
155
  "openai/gpt-4o-mini-transcribe",
147
156
  "openai/gpt-4o-transcribe",
148
157
  "openai/gpt-5",
149
158
  "openai/gpt-5-codex",
159
+ "openai/gpt-5-fast",
150
160
  "openai/gpt-5-mini",
161
+ "openai/gpt-5-mini-fast",
151
162
  "openai/gpt-5-nano",
152
163
  "openai/gpt-5-pro",
153
164
  "openai/gpt-5.1-codex",
154
165
  "openai/gpt-5.1-codex-max",
155
166
  "openai/gpt-5.1-codex-mini",
156
167
  "openai/gpt-5.1-thinking",
168
+ "openai/gpt-5.1-thinking-fast",
157
169
  "openai/gpt-5.2",
158
170
  "openai/gpt-5.2-codex",
171
+ "openai/gpt-5.2-fast",
159
172
  "openai/gpt-5.2-pro",
160
173
  "openai/gpt-5.3-codex",
174
+ "openai/gpt-5.3-codex-fast",
161
175
  "openai/gpt-5.4",
176
+ "openai/gpt-5.4-fast",
162
177
  "openai/gpt-5.4-mini",
178
+ "openai/gpt-5.4-mini-fast",
163
179
  "openai/gpt-5.4-nano",
164
180
  "openai/gpt-5.4-pro",
165
181
  "openai/gpt-5.5",
182
+ "openai/gpt-5.5-fast",
166
183
  "openai/gpt-5.5-pro",
167
184
  "openai/gpt-5.6-luna",
185
+ "openai/gpt-5.6-luna-fast",
168
186
  "openai/gpt-5.6-sol",
187
+ "openai/gpt-5.6-sol-fast",
169
188
  "openai/gpt-5.6-terra",
189
+ "openai/gpt-5.6-terra-fast",
170
190
  "openai/gpt-oss-120b",
171
191
  "openai/gpt-oss-20b",
172
192
  "openai/gpt-oss-safeguard-20b",
@@ -178,9 +198,11 @@ var VERCEL_GATEWAY_CHAT_MODELS = [
178
198
  "openai/o1",
179
199
  "openai/o3",
180
200
  "openai/o3-deep-research",
201
+ "openai/o3-fast",
181
202
  "openai/o3-mini",
182
203
  "openai/o3-pro",
183
204
  "openai/o4-mini",
205
+ "openai/o4-mini-fast",
184
206
  "openai/tts-1",
185
207
  "openai/tts-1-hd",
186
208
  "openai/whisper-1",
@@ -206,6 +228,7 @@ var VERCEL_GATEWAY_CHAT_MODELS = [
206
228
  "xai/grok-4.20-reasoning-beta",
207
229
  "xai/grok-4.3",
208
230
  "xai/grok-4.5",
231
+ "xai/grok-4.6",
209
232
  "xai/grok-build-0.1",
210
233
  "xai/grok-stt",
211
234
  "xai/grok-tts",
@@ -277,6 +300,7 @@ var VERCEL_GATEWAY_MODEL_TAGS = [
277
300
  "structured-output",
278
301
  "tool-use",
279
302
  "video-generation",
303
+ "video-input",
280
304
  "vision",
281
305
  "web-search",
282
306
  "websocket-realtime",