amazon-bedrock | { aliases: readonly ["amazon-bedrock", "bedrock"]; auth: { required: true; type: "bearer"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly ["standard", "flex", "priority"]; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "amazon-bedrock"; modelRules: readonly []; name: "Amazon Bedrock"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; request: { serviceTierMap: { auto: null; flex: "flex"; priority: "priority"; standard: "default"; }; }; requiresApiURL: true; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.aws.amazon.com/bedrock/latest/userguide/inference-chat-completions-mantle.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/service-tiers-inference.html"]; transport: "openai-chat"; } |
anthropic | { aliases: readonly ["anthropic", "claude"]; auth: { required: true; type: "x-api-key"; }; baseURL: "https://api.anthropic.com"; capabilities: { caching: { cacheBreakpoints: true; types: readonly ["ephemeral"]; }; functions: true; images: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: true; }; defaults: { model: "claude-sonnet-4-5"; }; headers: { anthropic-beta: "structured-outputs-2025-11-13, web-search-2025-03-05"; anthropic-version: "2023-06-01"; }; id: "anthropic"; modelRules: readonly []; name: "Anthropic"; operations: { chat: { dialect: "anthropic-messages"; path: "/v1/messages"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.anthropic.com/en/api/messages"]; transport: "anthropic-messages"; } |
azure-foundry | { aliases: readonly ["azure-foundry", "azure-ai-foundry", "microsoft-foundry"]; auth: { header: "api-key"; required: true; type: "api-key-header"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly ["standard", "priority"]; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "azure-foundry"; modelRules: readonly []; name: "Azure AI Foundry"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; request: { serviceTierMap: { auto: "auto"; flex: "flex"; priority: "priority"; standard: "default"; }; }; requiresApiURL: true; reviewedAt: "2026-08-17"; sources: readonly ["https://learn.microsoft.com/en-us/rest/api/microsoft-foundry/azureopenai/chat", "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/priority-processing"]; transport: "openai-chat"; } |
azure-openai | { aliases: readonly ["azure-openai", "azure_openai", "azure"]; auth: { header: "api-key"; required: true; type: "api-key-header"; }; baseURL: null; capabilities: { functions: true; images: true; multiTurn: true; serviceTiers: readonly ["standard", "priority"]; streaming: true; structuredOutputModes: readonly ["native", "function"]; structuredOutputs: true; thinking: true; }; capabilityGates: { structuredOutputs: { min: "2024-08-01"; option: "version"; }; }; defaults: { embedModel: "text-embedding-3-small"; model: "gpt-5-mini"; }; endpoint: { apiVersionField: "version"; defaults: { version: "2024-02-15-preview"; }; fields: { deploymentName: readonly ["deployment_name", "deploymentName"]; resourceName: readonly ["resource_name", "resourceName"]; version: readonly ["api_version", "apiVersion", "version"]; }; hostField: "resourceName"; hostSuffix: ".openai.azure.com"; normalizers: { version: "api-version"; }; path: "/openai/deployments/{deploymentName}"; required: readonly ["resourceName", "deploymentName"]; scheme: "https"; }; id: "azure-openai"; modelRules: readonly []; name: "Azure OpenAI"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; embed: { dialect: "openai-embeddings"; path: "/embeddings"; }; }; request: { serviceTierMap: { auto: "auto"; flex: "flex"; priority: "priority"; standard: "default"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://learn.microsoft.com/en-us/azure/ai-services/openai/reference", "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/priority-processing"]; transport: "openai-chat"; } |
baseten | { aliases: readonly ["baseten"]; auth: { required: true; type: "bearer"; }; baseURL: "https://inference.baseten.co/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["native", "function"]; structuredOutputs: true; thinking: false; }; defaults: { model: ""; }; id: "baseten"; modelRules: readonly []; name: "Baseten Model APIs"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.baseten.co/inference/model-apis/overview"]; transport: "openai-chat"; } |
baseten-engine | { aliases: readonly ["baseten-engine", "truss"]; auth: { required: false; type: "bearer"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "baseten-engine"; modelRules: readonly []; name: "Baseten Inference Engine"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: true; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.baseten.co/development/model/deployment/inference"]; transport: "openai-chat"; } |
cerebras | { aliases: readonly ["cerebras"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.cerebras.ai/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly ["standard", "flex", "priority"]; streaming: true; structuredOutputModes: readonly ["native", "function"]; structuredOutputs: true; thinking: false; }; defaults: { model: ""; }; id: "cerebras"; modelRules: readonly [{ capabilities: { thinking: true; thinkingBudget: true; }; match: { exact: readonly ["gpt-oss-120b"]; }; request: { defaultThinkingLevel: "max"; effortMap: { high: "high"; highest: "high"; low: "low"; max: "high"; medium: "medium"; minimal: "low"; none: null; xhigh: "high"; }; reasoning: "effort"; unsupportedThinkingLevels: { none: "Cerebras GPT-OSS reasoning does not support the none effort level"; }; }; }, { capabilities: { thinking: true; thinkingBudget: true; }; match: { exact: readonly ["gemma-4-31b"]; }; request: { defaultThinkingLevel: "max"; effortMap: { high: "high"; highest: "high"; low: "high"; max: "high"; medium: "high"; minimal: "high"; none: "none"; xhigh: "high"; }; reasoning: "effort"; }; }]; name: "Cerebras Inference"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; request: { serviceTierMap: { auto: "auto"; flex: "flex"; priority: "priority"; standard: "default"; }; }; requiresApiURL: false; reviewedAt: "2026-08-18"; sources: readonly ["https://inference-docs.cerebras.ai/capabilities/reasoning", "https://inference-docs.cerebras.ai/api-reference/chat-completions", "https://inference-docs.cerebras.ai/capabilities/service-tiers"]; transport: "openai-chat"; } |
cloudflare-workers-ai | { aliases: readonly ["cloudflare-workers-ai", "workers-ai"]; auth: { required: true; type: "bearer"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "cloudflare-workers-ai"; modelRules: readonly []; name: "Cloudflare Workers AI"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: true; reviewedAt: "2026-08-17"; sources: readonly ["https://developers.cloudflare.com/workers-ai/configuration/open-ai-compatibility/"]; transport: "openai-chat"; } |
cohere | { aliases: readonly ["cohere"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.cohere.ai/compatibility/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { embedModel: "embed-english-v3.0"; model: "command-r-plus"; }; id: "cohere"; modelRules: readonly []; name: "Cohere"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; embed: { dialect: "openai-embeddings"; path: "/embeddings"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.cohere.com/reference/compatibility-api"]; transport: "openai-chat"; } |
databricks | { aliases: readonly ["databricks"]; auth: { required: true; type: "bearer"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly ["standard", "priority"]; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "databricks"; modelRules: readonly []; name: "Databricks Model Serving"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; request: { serviceTierMap: { auto: null; priority: "priority"; standard: "default"; }; }; requiresApiURL: true; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.databricks.com/aws/en/machine-learning/model-serving/query-chat-models", "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/priority-mode"]; transport: "openai-chat"; } |
deepinfra | { aliases: readonly ["deepinfra"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.deepinfra.com/v1/openai"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly ["standard", "priority"]; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "deepinfra"; modelRules: readonly [{ capabilities: { thinking: true; thinkingBudget: true; }; match: { prefix: readonly ["deepseek-ai/DeepSeek-R1"]; }; request: { defaultThinkingLevel: "max"; effortMap: { high: "high"; highest: "high"; low: "low"; max: "high"; medium: "medium"; minimal: "low"; none: "none"; xhigh: "high"; }; reasoning: "effort"; }; }]; name: "DeepInfra"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; request: { serviceTierMap: { auto: null; priority: "priority"; standard: null; }; }; requiresApiURL: false; reviewedAt: "2026-08-18"; sources: readonly ["https://docs.deepinfra.com/chat/reasoning", "https://docs.deepinfra.com/api-reference/introduction", "https://docs.deepinfra.com/chat/overview"]; transport: "openai-chat"; } |
deepseek | { aliases: readonly ["deepseek"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.deepseek.com"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function", "json_object"]; structuredOutputs: false; thinking: false; }; defaults: { model: "deepseek-v4-flash"; }; id: "deepseek"; modelRules: readonly [{ capabilities: { showThoughts: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: true; thinkingBudget: true; }; match: { exact: readonly ["deepseek-v4-flash", "deepseek-v4-pro"]; }; replay: { assistantReasoningField: "reasoning_content"; }; request: { defaultThinkingLevel: "max"; dropWhenThinking: readonly ["temperature", "top_p", "presence_penalty", "frequency_penalty"]; effortMap: { high: "high"; highest: "max"; low: "low"; max: "max"; medium: "medium"; minimal: "low"; none: null; xhigh: "max"; }; reasoning: "thinking-object"; toolChoice: "unforced"; }; response: { reasoningFields: readonly ["reasoning_content", "reasoning"]; }; }, { capabilities: { showThoughts: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: true; thinkingBudget: false; }; match: { exact: readonly ["deepseek-reasoner"]; }; replay: { assistantReasoningField: "reasoning_content"; }; request: { toolChoice: "unforced"; }; response: { reasoningFields: readonly ["reasoning_content", "reasoning"]; }; }]; name: "DeepSeek"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-18"; sources: readonly ["https://api-docs.deepseek.com/guides/thinking_mode/"]; transport: "openai-chat"; } |
deepseek-responses | { aliases: readonly ["deepseek-responses", "deepseek_responses"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.deepseek.com"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: true; }; defaults: { model: "deepseek-v4-flash"; }; id: "deepseek-responses"; modelRules: readonly []; name: "DeepSeek Responses"; operations: { chat: { dialect: "openai-responses"; path: "/responses"; }; }; request: { dropFields: readonly ["include", "previous_response_id", "store", "parallel_tool_calls"]; reasoningObjectFields: readonly ["effort"]; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://api-docs.deepseek.com/api/create-chat-completion"]; transport: "openai-responses"; } |
featherless | { aliases: readonly ["featherless", "featherless-ai"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.featherless.ai/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "featherless"; modelRules: readonly []; name: "Featherless AI"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://featherless.ai/docs/quickstart-guide"]; transport: "openai-chat"; } |
fireworks | { aliases: readonly ["fireworks", "fireworks-ai"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.fireworks.ai/inference/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly ["standard", "priority"]; streaming: true; structuredOutputModes: readonly ["native", "function"]; structuredOutputs: true; thinking: false; }; defaults: { model: ""; }; id: "fireworks"; modelRules: readonly [{ capabilities: { showThoughts: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: true; thinkingBudget: true; }; match: { contains: readonly ["deepseek-v4"]; }; replay: { assistantReasoningField: "reasoning_content"; }; request: { defaultThinkingLevel: "max"; effortMap: { high: "high"; highest: "max"; low: "high"; max: "max"; medium: "high"; minimal: "high"; none: "none"; xhigh: "max"; }; reasoning: "effort"; toolChoice: "unforced"; }; response: { reasoningFields: readonly ["reasoning_content", "reasoning"]; }; }]; name: "Fireworks AI"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; embed: { dialect: "openai-embeddings"; path: "/embeddings"; }; }; request: { serviceTierMap: { auto: null; priority: "priority"; standard: "default"; }; }; requiresApiURL: false; reviewedAt: "2026-08-18"; sources: readonly ["https://docs.fireworks.ai/api-reference/post-chatcompletions", "https://docs.fireworks.ai/guides/reasoning"]; transport: "openai-chat"; } |
friendli | { aliases: readonly ["friendli", "friendli-ai"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.friendli.ai/serverless/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "friendli"; modelRules: readonly []; name: "FriendliAI"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://friendli.ai/docs/guides/tool-calling"]; transport: "openai-chat"; } |
google-gemini | { aliases: readonly ["google-gemini", "google_gemini", "gemini"]; auth: { header: "x-goog-api-key"; required: true; type: "api-key-header"; }; baseURL: "https://generativelanguage.googleapis.com/v1beta"; capabilities: { audio: true; audioOutput: true; caching: { types: readonly ["persistent"]; }; files: { uploadMethod: "cloud"; }; functions: true; images: true; multiTurn: true; serviceTiers: readonly ["standard", "flex", "priority"]; streaming: true; structuredOutputModes: readonly ["native", "function"]; structuredOutputs: true; thinking: true; }; defaults: { embedModel: "gemini-embedding-2"; model: "gemini-3.5-flash"; }; id: "google-gemini"; modelRules: readonly []; name: "Google Gemini"; operations: { chat: { dialect: "gemini-generate-content"; path: "/models/{model}:generateContent"; }; embed: { dialect: "gemini-generate-content"; path: "/models/{model}:batchEmbedContents"; }; realtime: { audio: { input: { formats: readonly ["pcm16", "pcm"]; sampleRate: 16000; }; output: { defaultVoice: "Kore"; formats: readonly ["pcm16", "pcm"]; sampleRate: 24000; voices: readonly ["Kore", "Puck", "Charon", "Fenrir", "Aoede"]; }; }; defaultModel: "gemini-2.5-flash-native-audio-preview-12-2025"; dialect: "gemini-live-bidi"; grammar: "gemini_live_bidi"; modelMatch: { contains: readonly ["native-audio", "-live-"]; prefix: readonly ["gemini-live"]; }; path: "/ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent"; url: "wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent"; validation: { pcmInputOnly: true; rejectStructuredOutputWithAudio: true; }; }; speak: { dialect: "gemini-generate-content"; path: "/models/{model}:generateContent"; }; stream_chat: { dialect: "gemini-generate-content"; path: "/models/{model}:streamGenerateContent?alt=sse"; }; transcribe: { dialect: "gemini-generate-content"; path: "/models/{model}:generateContent"; }; }; request: { serviceTierMap: { auto: null; flex: "flex"; priority: "priority"; standard: "standard"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://ai.google.dev/api/generate-content", "https://ai.google.dev/gemini-api/docs/optimization"]; transport: "gemini-generate-content"; } |
grok | { aliases: readonly ["grok", "xai", "x-grok", "x_grok"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.x.ai/v1"; capabilities: { audio: true; audioOutput: true; functions: true; images: true; multiTurn: true; serviceTiers: readonly ["standard", "priority"]; streaming: true; structuredOutputModes: readonly ["native", "function"]; structuredOutputs: true; thinking: false; webSearch: true; }; defaults: { model: "grok-4.6"; }; id: "grok"; modelRules: readonly [{ capabilities: { structuredOutputModes: readonly ["native", "function"]; structuredOutputs: true; thinking: true; thinkingBudget: true; }; match: { exact: readonly ["grok-4.6"]; }; request: { defaultThinkingLevel: "max"; dropFields: readonly ["presence_penalty", "frequency_penalty", "stop"]; effortMap: { high: "high"; highest: "xhigh"; low: "low"; max: "xhigh"; medium: "medium"; minimal: "low"; none: null; xhigh: "xhigh"; }; reasoning: "effort"; unsupportedThinkingLevels: { none: "xAI Grok 4.6 reasoning cannot be disabled"; }; }; }, { capabilities: { structuredOutputModes: readonly ["native", "function"]; structuredOutputs: true; thinking: true; thinkingBudget: true; }; match: { exact: readonly ["grok-4.5", "grok-4.5-latest", "grok-build-latest"]; }; request: { defaultThinkingLevel: "max"; dropFields: readonly ["presence_penalty", "frequency_penalty", "stop"]; effortMap: { high: "high"; highest: "high"; low: "low"; max: "high"; medium: "medium"; minimal: "low"; none: null; xhigh: "high"; }; reasoning: "effort"; unsupportedThinkingLevels: { none: "xAI Grok 4.5 reasoning cannot be disabled"; }; }; }, { capabilities: { showThoughts: true; structuredOutputModes: readonly ["native", "function"]; structuredOutputs: true; thinking: true; thinkingBudget: true; }; match: { exact: readonly ["grok-4.3", "grok-4.3-latest", "grok-latest"]; }; request: { defaultThinkingLevel: "max"; dropFields: readonly ["presence_penalty", "frequency_penalty", "stop"]; effortMap: { high: "high"; highest: "high"; low: "low"; max: "high"; medium: "medium"; minimal: "low"; none: "none"; xhigh: "high"; }; reasoning: "effort"; }; }, { capabilities: { thinking: true; thinkingBudget: true; }; match: { exact: readonly ["grok-3-mini", "grok-3-mini-latest", "grok-3-mini-beta", "grok-3-mini-fast", "grok-3-mini-fast-latest", "grok-3-mini-fast-beta"]; }; request: { defaultThinkingLevel: "low"; effortMap: { high: "high"; highest: "high"; low: "low"; max: "high"; medium: "high"; minimal: "low"; none: null; xhigh: "high"; }; reasoning: "effort"; unsupportedThinkingLevels: { none: "xAI Grok 3 Mini reasoning cannot be disabled"; }; }; }]; name: "xAI Grok"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; realtime: { audio: { input: { formats: readonly ["pcm16", "pcm"]; sampleRate: 24000; }; output: { defaultVoice: "eve"; formats: readonly ["pcm16", "pcm"]; sampleRate: 24000; voices: readonly ["eve", "ara", "rex", "sal", "leo"]; }; }; defaultModel: "grok-voice-think-fast-1.0"; dialect: "xai-realtime"; grammar: "openai_realtime_compatible"; modelMatch: { prefix: readonly ["grok-voice"]; }; path: "/realtime"; url: "wss://api.x.ai/v1/realtime"; validation: { structuredOutputWithAudio: false; }; }; speak: { dialect: "xai-speech"; path: "/tts"; }; transcribe: { dialect: "xai-transcription"; path: "/stt"; }; }; request: { optionDialect: "search-parameters"; serviceTierMap: { auto: null; priority: "priority"; standard: "default"; }; }; requiresApiURL: false; reviewedAt: "2026-08-30"; sources: readonly ["https://docs.x.ai/developers/model-capabilities/text/reasoning", "https://docs.x.ai/developers/rest-api-reference/management/auth", "https://docs.x.ai/developers/models/grok-4.5", "https://docs.x.ai/developers/advanced-api-usage/priority-processing"]; transport: "openai-chat"; } |
groq | { aliases: readonly ["groq"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.groq.com/openai/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly ["standard", "flex", "priority"]; streaming: true; structuredOutputModes: readonly ["native", "function"]; structuredOutputs: true; thinking: false; }; defaults: { model: ""; }; id: "groq"; modelRules: readonly [{ capabilities: { thinking: true; thinkingBudget: true; }; match: { exact: readonly ["openai/gpt-oss-20b", "openai/gpt-oss-120b"]; }; request: { defaultThinkingLevel: "max"; effortMap: { high: "high"; highest: "high"; low: "low"; max: "high"; medium: "medium"; minimal: "low"; none: null; xhigh: "high"; }; reasoning: "effort"; unsupportedThinkingLevels: { none: "Groq GPT-OSS reasoning does not support the none effort level"; }; }; }, { capabilities: { thinking: true; thinkingBudget: true; }; match: { exact: readonly ["qwen/qwen3.6-27b"]; }; request: { defaultThinkingLevel: "max"; effortMap: { high: "default"; highest: "default"; low: "default"; max: "default"; medium: "default"; minimal: "default"; none: "none"; xhigh: "default"; }; reasoning: "effort"; }; }]; name: "Groq"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; request: { serviceTierMap: { auto: "auto"; flex: "flex"; priority: "performance"; standard: "on_demand"; }; }; requiresApiURL: false; reviewedAt: "2026-08-18"; sources: readonly ["https://console.groq.com/docs/reasoning", "https://console.groq.com/docs/api-reference", "https://console.groq.com/docs/service-tiers"]; transport: "openai-chat"; } |
huggingface-router | { aliases: readonly ["huggingface-router", "huggingface", "hf-router"]; auth: { required: true; type: "bearer"; }; baseURL: "https://router.huggingface.co/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "huggingface-router"; modelRules: readonly []; name: "Hugging Face Router"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-18"; sources: readonly ["https://huggingface.co/docs/inference-providers/en/index", "https://huggingface.co/docs/inference-providers/en/tasks/chat-completion"]; transport: "openai-chat"; } |
hyperbolic | { aliases: readonly ["hyperbolic"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.hyperbolic.xyz/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "hyperbolic"; modelRules: readonly []; name: "Hyperbolic"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.hyperbolic.xyz/docs/inference-api"]; transport: "openai-chat"; } |
llama-cpp | { aliases: readonly ["llama-cpp", "llama.cpp"]; auth: { required: false; type: "bearer"; }; baseURL: "http://localhost:8080/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "llama-cpp"; modelRules: readonly []; name: "llama.cpp Server"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md"]; transport: "openai-chat"; } |
lm-studio | { aliases: readonly ["lm-studio", "lmstudio"]; auth: { required: false; type: "bearer"; }; baseURL: "http://localhost:1234/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "lm-studio"; modelRules: readonly []; name: "LM Studio"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://lmstudio.ai/docs/developer/openai-compat"]; transport: "openai-chat"; } |
localai | { aliases: readonly ["localai", "local-ai"]; auth: { required: false; type: "bearer"; }; baseURL: "http://localhost:8080/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "localai"; modelRules: readonly []; name: "LocalAI"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://localai.io/features/openai-functions/"]; transport: "openai-chat"; } |
mistral | { aliases: readonly ["mistral"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.mistral.ai/v1"; capabilities: { audio: true; audioOutput: true; functions: true; images: true; multiTurn: true; serviceTiers: readonly ["standard", "priority"]; streaming: true; structuredOutputModes: readonly ["native", "function"]; structuredOutputs: true; thinking: false; }; defaults: { embedModel: "mistral-embed"; model: "mistral-small-latest"; }; id: "mistral"; modelRules: readonly []; name: "Mistral AI"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; embed: { dialect: "openai-embeddings"; path: "/embeddings"; }; speak: { dialect: "mistral-speech"; path: "/audio/speech"; }; transcribe: { dialect: "openai-transcription"; path: "/audio/transcriptions"; }; }; request: { imageURLShape: "object"; renameFields: { max_completion_tokens: "max_tokens"; }; serviceTierMap: { auto: "auto"; priority: "auto"; standard: "standard_only"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.mistral.ai/api/", "https://docs.mistral.ai/inference/priority-tier"]; transport: "openai-chat"; } |
nebius | { aliases: readonly ["nebius"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.tokenfactory.nebius.com/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "nebius"; modelRules: readonly []; name: "Nebius AI Studio"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://api.studio.nebius.com/docs"]; transport: "openai-chat"; } |
novita | { aliases: readonly ["novita", "novita-ai"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.novita.ai/v3/openai"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "novita"; modelRules: readonly []; name: "Novita AI"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://novita.ai/docs/guides/llm-api"]; transport: "openai-chat"; } |
nscale | { aliases: readonly ["nscale"]; auth: { required: true; type: "bearer"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "nscale"; modelRules: readonly []; name: "Nscale"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: true; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.nscale.com/docs/use-cases/chat"]; transport: "openai-chat"; } |
nvidia-nim | { aliases: readonly ["nvidia-nim", "nim"]; auth: { required: false; type: "bearer"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "nvidia-nim"; modelRules: readonly []; name: "NVIDIA NIM"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: true; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.nvidia.com/nim/large-language-models/latest/getting-started.html"]; transport: "openai-chat"; } |
ollama | { aliases: readonly ["ollama"]; auth: { required: false; type: "bearer"; }; baseURL: "http://localhost:11434/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "ollama"; modelRules: readonly []; name: "Ollama"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.ollama.com/api/openai-compatibility"]; transport: "openai-chat"; } |
openai | { aliases: readonly ["openai"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.openai.com/v1"; capabilities: { audio: true; audioOutput: true; functions: true; images: true; multiTurn: true; serviceTiers: readonly ["standard", "flex", "priority"]; streaming: true; structuredOutputModes: readonly ["native", "function", "json_object"]; structuredOutputs: true; thinking: true; }; defaults: { embedModel: "text-embedding-3-small"; model: "gpt-5-mini"; }; id: "openai"; modelRules: readonly []; name: "OpenAI"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; embed: { dialect: "openai-embeddings"; path: "/embeddings"; }; realtime: { audio: { input: { formats: readonly ["pcm16", "pcm"]; sampleRate: 24000; }; output: { defaultVoice: "alloy"; formats: readonly ["pcm16", "pcm"]; sampleRate: 24000; voices: readonly ["alloy", "ash", "ballad", "coral", "echo", "sage", "shimmer", "verse"]; }; }; dialect: "openai-realtime"; grammar: "openai_realtime_compatible"; modelMatch: { prefix: readonly ["gpt-realtime"]; }; path: "/realtime"; url: "wss://api.openai.com/v1/realtime"; validation: { structuredOutputWithAudio: false; }; }; speak: { dialect: "openai-speech"; path: "/audio/speech"; }; transcribe: { dialect: "openai-transcription"; path: "/audio/transcriptions"; }; }; request: { serviceTierMap: { auto: "auto"; flex: "flex"; priority: "priority"; standard: "default"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://platform.openai.com/docs/api-reference/chat"]; transport: "openai-chat"; } |
openai-compatible | { aliases: readonly ["openai-compatible", "openai_compatible", "compatible"]; auth: { required: false; type: "bearer"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "openai-compatible"; modelRules: readonly []; name: "OpenAI Compatible"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; embed: { dialect: "openai-embeddings"; path: "/embeddings"; }; }; requiresApiURL: true; reviewedAt: "2026-08-17"; sources: readonly ["https://platform.openai.com/docs/api-reference/chat"]; transport: "openai-chat"; } |
openai-responses | { aliases: readonly ["openai-responses", "openai_responses", "responses"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.openai.com/v1"; capabilities: { audio: true; audioOutput: true; functions: true; images: true; multiTurn: true; serviceTiers: readonly ["standard", "flex", "priority"]; streaming: true; structuredOutputModes: readonly ["native", "function", "json_object"]; structuredOutputs: true; thinking: true; }; defaults: { embedModel: "text-embedding-3-small"; model: "gpt-5-mini"; }; id: "openai-responses"; modelRules: readonly []; name: "OpenAI Responses"; operations: { chat: { dialect: "openai-responses"; path: "/responses"; }; embed: { dialect: "openai-embeddings"; path: "/embeddings"; }; realtime: { audio: { input: { formats: readonly ["pcm16", "pcm"]; sampleRate: 24000; }; output: { defaultVoice: "alloy"; formats: readonly ["pcm16", "pcm"]; sampleRate: 24000; voices: readonly ["alloy", "ash", "ballad", "coral", "echo", "sage", "shimmer", "verse"]; }; }; dialect: "openai-realtime"; grammar: "openai_realtime_compatible"; modelMatch: { prefix: readonly ["gpt-realtime"]; }; path: "/realtime"; url: "wss://api.openai.com/v1/realtime"; validation: { structuredOutputWithAudio: false; }; }; speak: { dialect: "openai-speech"; path: "/audio/speech"; }; transcribe: { dialect: "openai-transcription"; path: "/audio/transcriptions"; }; }; request: { serviceTierMap: { auto: "auto"; flex: "flex"; priority: "priority"; standard: "default"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://platform.openai.com/docs/api-reference/responses"]; transport: "openai-responses"; } |
openrouter | { aliases: readonly ["openrouter"]; auth: { required: true; type: "bearer"; }; baseURL: "https://openrouter.ai/api/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly ["standard", "flex", "priority"]; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "openrouter"; modelRules: readonly [{ capabilities: { showThoughts: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: true; thinkingBudget: true; }; match: { prefix: readonly ["deepseek/"]; }; replay: { assistantReasoningDetailsField: "reasoning_details"; assistantReasoningField: "reasoning"; }; request: { defaultThinkingLevel: "max"; effortMap: { high: "high"; highest: "max"; low: "low"; max: "max"; medium: "medium"; minimal: "low"; none: "none"; xhigh: "xhigh"; }; reasoning: "openrouter"; toolChoice: "unforced"; }; response: { reasoningDetailsFields: readonly ["reasoning_details"]; reasoningFields: readonly ["reasoning", "reasoning_content"]; }; }]; name: "OpenRouter"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; request: { serviceTierMap: { auto: null; flex: "flex"; priority: "priority"; standard: null; }; }; requiresApiURL: false; reviewedAt: "2026-08-18"; sources: readonly ["https://openrouter.ai/docs/guides/best-practices/reasoning-tokens", "https://openrouter.ai/docs/guides/features/service-tiers"]; transport: "openai-chat"; } |
orcarouter | { aliases: readonly ["orcarouter"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.orcarouter.ai/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: "orcarouter/auto"; }; id: "orcarouter"; modelRules: readonly []; name: "OrcaRouter"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-19"; sources: readonly ["https://www.orcarouter.ai"]; transport: "openai-chat"; } |
ovhcloud | { aliases: readonly ["ovhcloud", "ovh"]; auth: { required: true; type: "bearer"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "ovhcloud"; modelRules: readonly []; name: "OVHcloud AI Endpoints"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: true; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-capabilities"]; transport: "openai-chat"; } |
reka | { aliases: readonly ["reka"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.reka.ai/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: "reka-core"; }; id: "reka"; modelRules: readonly []; name: "Reka"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.reka.ai/"]; transport: "openai-chat"; } |
runpod-vllm | { aliases: readonly ["runpod-vllm", "runpod"]; auth: { required: true; type: "bearer"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "runpod-vllm"; modelRules: readonly []; name: "RunPod vLLM"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: true; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.runpod.io/serverless/vllm/openai-compatibility"]; transport: "openai-chat"; } |
sagemaker-vllm | { aliases: readonly ["sagemaker-vllm", "sagemaker"]; auth: { required: false; type: "bearer"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "sagemaker-vllm"; modelRules: readonly []; name: "SageMaker vLLM"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: true; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints-openai-compatible.html"]; transport: "openai-chat"; } |
sambanova | { aliases: readonly ["sambanova", "sambanova-cloud"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.sambanova.ai/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "sambanova"; modelRules: readonly []; name: "SambaNova Cloud"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.sambanova.ai/docs/en/api-reference/overview"]; transport: "openai-chat"; } |
scaleway | { aliases: readonly ["scaleway"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.scaleway.ai/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "scaleway"; modelRules: readonly []; name: "Scaleway Generative APIs"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://www.scaleway.com/en/developers/api/generative-apis"]; transport: "openai-chat"; } |
siliconflow | { aliases: readonly ["siliconflow"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.siliconflow.com/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "siliconflow"; modelRules: readonly []; name: "SiliconFlow"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.siliconflow.com/en/userguide/quickstart"]; transport: "openai-chat"; } |
together | { aliases: readonly ["together", "together-ai", "together_ai"]; auth: { required: true; type: "bearer"; }; baseURL: "https://api.together.xyz/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["native", "function", "json_object"]; structuredOutputs: true; thinking: false; }; defaults: { model: ""; }; id: "together"; modelRules: readonly [{ capabilities: { showThoughts: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: true; thinkingBudget: true; }; match: { prefix: readonly ["deepseek-ai/DeepSeek-V4"]; }; replay: { assistantReasoningField: "reasoning"; }; request: { defaultThinkingLevel: "max"; effortMap: { high: "max"; highest: "max"; low: "high"; max: "max"; medium: "high"; minimal: "high"; none: null; xhigh: "max"; }; reasoning: "effort"; toolChoice: "unforced"; }; response: { reasoningFields: readonly ["reasoning", "reasoning_content"]; }; }]; name: "Together AI"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; embed: { dialect: "openai-embeddings"; path: "/embeddings"; }; }; requiresApiURL: false; reviewedAt: "2026-08-18"; sources: readonly ["https://docs.together.ai/docs/inference/chat/reasoning"]; transport: "openai-chat"; } |
vertex-ai | { aliases: readonly ["vertex-ai", "vertex-openai"]; auth: { required: true; type: "bearer"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "vertex-ai"; modelRules: readonly [{ capabilities: { structuredOutputModes: readonly ["json_object", "function"]; structuredOutputs: false; thinking: true; }; match: { exact: readonly ["google/gemma-4-26b-a4b-it-maas"]; }; replay: { assistantReasoningField: "reasoning_content"; }; request: { defaultThinkingLevel: "max"; thinkingBoolean: { path: readonly ["chat_template_kwargs", "enable_thinking"]; }; }; response: { reasoningFields: readonly ["reasoning_content"]; }; }, { capabilities: { structuredOutputModes: readonly ["native", "function", "json_object"]; structuredOutputs: true; }; match: { prefix: readonly ["google/gemini-", "gemini-"]; }; }]; name: "Vertex AI OpenAI Compatibility"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: true; reviewedAt: "2026-08-18"; sources: readonly ["https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/call-vertex-using-openai-library", "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/maas/capabilities/structured-output", "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/maas/capabilities/thinking"]; transport: "openai-chat"; } |
vllm | { aliases: readonly ["vllm"]; auth: { required: false; type: "bearer"; }; baseURL: "http://localhost:8000/v1"; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "vllm"; modelRules: readonly []; name: "vLLM"; operations: { chat: { dialect: "openai-chat"; path: "/chat/completions"; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://docs.vllm.ai/en/latest/serving/openai_compatible_server/"]; transport: "openai-chat"; } |
webllm | { aliases: readonly ["webllm"]; auth: { required: false; type: "none"; }; baseURL: null; capabilities: { functions: true; multiTurn: true; serviceTiers: readonly []; streaming: true; structuredOutputModes: readonly ["function"]; structuredOutputs: false; thinking: false; }; defaults: { model: ""; }; id: "webllm"; modelRules: readonly []; name: "WebLLM"; operations: { chat: { dialect: "webllm"; path: ""; }; }; requiresApiURL: false; reviewedAt: "2026-08-17"; sources: readonly ["https://webllm.mlc.ai/docs/"]; transport: "webllm"; } |