> ## Documentation Index > Fetch the complete documentation index at: https://docs.getbifrost.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create async chat completion > Submits a chat completion request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. Streaming is not supported for async requests. ## OpenAPI ````yaml /openapi/openapi.json post /v1/async/chat/completions openapi: 3.1.0 info: title: Bifrost API description: > Bifrost HTTP Transport API for AI model inference and gateway management. This API provides a unified interface for interacting with multiple AI providers including OpenAI, Anthropic, Bedrock, Gemini, and more through a single API, along with comprehensive management APIs for configuring and monitoring the gateway. ## API Structure ### Unified Inference API (`/v1/*`) The primary API using Bifrost's unified format. Model parameters use the format `provider/model` (e.g., `openai/gpt-4`, `anthropic/claude-3-opus`). ### Async Inference API (`/v1/async/*`) Submit inference requests for asynchronous execution. Returns a job ID immediately and allows polling for results. Supports all inference types except batches, files, and containers. ### Provider Integration APIs Native provider-format APIs for drop-in compatibility: - `/openai/*` - OpenAI-compatible API - `/anthropic/*` - Anthropic-compatible API - `/genai/*` - Google GenAI (Gemini) compatible API - `/bedrock/*` - AWS Bedrock compatible API - `/cohere/*` - Cohere compatible API ### Framework Integration APIs Multi-provider proxy endpoints for AI frameworks: - `/litellm/*` - LiteLLM proxy with all provider formats - `/langchain/*` - LangChain compatible endpoints - `/pydanticai/*` - PydanticAI compatible endpoints ### Management APIs (`/api/*`) APIs for managing and monitoring the Bifrost gateway: - `/api/config` - Configuration management - `/api/providers` - Provider and API key management - `/api/plugins` - Plugin management - `/api/governance/*` - Virtual keys, teams, customers, budgets, rate limits, routing rules, and pricing overrides - `/api/logs` - Log search and analytics - `/api/mcp/*` - MCP (Model Context Protocol) client management - `/api/session/*` - Authentication and session management - `/api/cache/*` - Cache management - `/health` - Health check endpoint ## Fallbacks Requests can include fallback models that will be tried if the primary model fails. version: 1.0.0 contact: name: Contact Us url: https://getmaxim.ai/bifrost license: name: Apache 2.0 url: https://opensource.org/licenses/Apache-2.0 servers: - url: '{baseUrl}' description: Your Bifrost instance variables: baseUrl: default: http://localhost:8080 description: Base URL of your Bifrost instance (e.g. https://bifrost.mycompany.com) security: - BearerAuth: [] - BasicAuth: [] - ApiKeyAuth: [] tags: - name: Models description: Model listing and information - name: Chat Completions description: Chat-based text generation - name: Text Completions description: Text completion generation - name: Responses description: OpenAI Responses API compatible endpoints - name: OCR description: Optical character recognition for documents and images - name: Rerank description: Document reranking by relevance to a query - name: Embeddings description: Text embedding generation - name: Images description: Image generations, editing, and variations - name: Videos description: Video generation and management - name: Audio description: Speech synthesis and transcription - name: Count Tokens description: Token counting utilities - name: Batch description: Batch processing operations - name: Files description: File management operations - name: Containers description: Container management operations - name: Async Jobs description: Asynchronous job submission and retrieval endpoints - name: Realtime description: Realtime WebSocket and WebRTC endpoints - name: OpenAI Integration description: OpenAI-compatible API endpoints (/openai/*) - name: Azure Integration description: Azure OpenAI integration endpoints - name: Anthropic Integration description: Anthropic-compatible API endpoints (/anthropic/*) - name: GenAI Integration description: Google GenAI (Gemini) compatible API endpoints (/genai/*) - name: Bedrock Integration description: AWS Bedrock compatible API endpoints (/bedrock/*) - name: Cohere Integration description: Cohere compatible API endpoints (/cohere/*) - name: LiteLLM Integration description: LiteLLM proxy endpoints with multi-provider support (/litellm/*) - name: LangChain Integration description: LangChain compatible endpoints with multi-provider support (/langchain/*) - name: PydanticAI Integration description: >- PydanticAI compatible endpoints with multi-provider support (/pydanticai/*) - name: Health description: Health check endpoints - name: Configuration description: Configuration management endpoints - name: Session description: Session and authentication endpoints - name: Providers description: Provider management endpoints - name: Plugins description: Plugin management endpoints - name: MCP description: Model Context Protocol endpoints - name: Governance description: Virtual keys, teams, and customers management - name: Logging description: Log search and management endpoints - name: Cache description: Cache management endpoints - name: Vault description: Vault secret management endpoints - name: Skills description: Skills Repository management, marketplace, and download endpoints - name: Audit Logs description: >- CADF-compliant audit log search, export, and signature verification endpoints - name: Webhooks description: Webhook endpoint management and signed async-job delivery history paths: /v1/async/chat/completions: post: tags: - Async Jobs summary: Create async chat completion description: > Submits a chat completion request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. Streaming is not supported for async requests. operationId: createAsyncChatCompletion parameters: - $ref: '#/components/parameters/AsyncResultTTL' - $ref: '#/components/parameters/AsyncWebhookEndpoint' requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' responses: '202': description: Job accepted for processing content: application/json: schema: $ref: '#/components/schemas/AsyncJobResponse' '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/BifrostError' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/BifrostError' security: - BearerAuth: [] - BasicAuth: [] - VirtualKeyAuth: [] - ApiKeyAuth: [] components: parameters: AsyncResultTTL: name: x-bf-async-job-result-ttl in: header required: false description: > Time-to-live in seconds for the job result after completion. Defaults to 3600 (1 hour). After expiry, the job result is automatically cleaned up. schema: type: integer default: 3600 AsyncWebhookEndpoint: name: x-bf-async-webhook in: header required: false description: > Name of a registered webhook endpoint to notify when this job reaches a terminal state (`completed` or `failed`). The endpoint must already exist and be enabled; otherwise the submission is rejected with HTTP 400. If the endpoint is not subscribed to the resulting event, the job still completes normally but no delivery is enqueued. When omitted, no webhook is sent for the job and results are retrieved by polling. See the Webhooks management API to register endpoints. schema: type: string schemas: ChatCompletionRequest: type: object required: - model - messages properties: model: type: string description: Model in provider/model format (e.g., openai/gpt-4) example: openai/gpt-4 messages: type: array items: $ref: '#/components/schemas/ChatMessage' description: List of messages in the conversation fallbacks: type: array items: type: string description: Fallback models in provider/model format stream: type: boolean description: Whether to stream the response frequency_penalty: type: number minimum: -2 maximum: 2 logit_bias: type: object additionalProperties: type: number logprobs: type: boolean max_completion_tokens: type: integer metadata: type: object additionalProperties: true modalities: type: array items: type: string parallel_tool_calls: type: boolean presence_penalty: type: number minimum: -2 maximum: 2 prompt_cache_key: type: string reasoning: type: object properties: effort: type: string description: Reasoning effort level enum: - none - minimal - low - medium - high - xhigh max_tokens: type: integer response_format: type: object description: Format for the response safety_identifier: type: string service_tier: type: string stream_options: type: object properties: include_obfuscation: type: boolean include_usage: type: boolean store: type: boolean temperature: type: number minimum: 0 maximum: 2 tool_choice: oneOf: - type: string enum: - none - auto - required - type: object required: - type properties: type: type: string enum: - none - any - required - function - allowed_tools - custom function: type: object required: - name properties: name: type: string allowed_tools: type: object properties: mode: type: string enum: - auto - required tools: type: array items: type: object required: - type properties: type: type: string function: type: object required: - name properties: name: type: string tools: type: array items: type: object required: - type properties: type: type: string enum: - function - custom function: type: object required: - name properties: name: type: string description: type: string parameters: type: object properties: type: type: string description: type: string required: type: array items: type: string properties: type: object additionalProperties: true enum: type: array items: type: string additionalProperties: type: boolean strict: type: boolean custom: type: object properties: format: type: object required: - type properties: type: type: string grammar: type: object required: - definition - syntax properties: definition: type: string syntax: type: string enum: - lark - regex cache_control: $ref: '#/components/schemas/CacheControl' seed: type: integer description: Deterministic sampling seed top_p: type: number minimum: 0 maximum: 1 description: Nucleus sampling parameter top_logprobs: type: integer minimum: 0 maximum: 20 description: Number of most likely tokens to return at each position stop: oneOf: - type: string - type: array items: type: string description: Up to 4 sequences where the API will stop generating tokens prediction: type: object description: >- Predicted output content for the model to reference (OpenAI only). Can reduce latency. properties: type: type: string description: Always "content" content: description: Predicted content (string or array of content parts) oneOf: - type: string - type: array items: type: object additionalProperties: true prompt_cache_retention: type: string enum: - in_memory - 24h description: Prompt cache retention policy web_search_options: type: object description: Web search options for chat completions (OpenAI only) properties: search_context_size: type: string enum: - low - medium - high description: Amount of search context to include user_location: type: object properties: type: type: string description: Location type (e.g., "approximate") approximate: type: object properties: city: type: string country: type: string description: Two-letter ISO country code (e.g., "US") region: type: string description: Region or state (e.g., "California") timezone: type: string description: IANA timezone (e.g., "America/Los_Angeles") truncation: type: string user: type: string verbosity: type: string enum: - low - medium - high AsyncJobResponse: type: object description: Response returned when creating or polling an async job required: - id - status - created_at properties: id: type: string description: Unique identifier for the async job status: $ref: '#/components/schemas/AsyncJobStatus' expires_at: type: string format: date-time description: When the job result expires and will be cleaned up created_at: type: string format: date-time description: When the job was created completed_at: type: string format: date-time description: When the job completed (successfully or with failure) status_code: type: integer description: HTTP status code of the completed operation result: description: >- The result of the completed operation (shape depends on the request type) error: $ref: '#/components/schemas/BifrostError' BifrostError: type: object description: Error response from Bifrost properties: event_id: type: string type: type: string is_bifrost_error: type: boolean status_code: type: integer error: $ref: '#/components/schemas/ErrorField' extra_fields: $ref: '#/components/schemas/BifrostErrorExtraFields' ChatMessage: type: object required: - role properties: role: type: string enum: - assistant - user - system - tool - developer name: type: string content: oneOf: - type: string - type: array items: type: object required: - type properties: type: type: string enum: - text - image_url - input_audio - file - refusal text: type: string refusal: type: string image_url: type: object required: - url properties: url: type: string detail: type: string enum: - low - high - auto input_audio: type: object required: - data properties: data: type: string format: type: string file: type: object properties: file_data: type: string file_id: type: string filename: type: string file_type: type: string cache_control: $ref: '#/components/schemas/CacheControl' description: Message content - can be a string or array of content blocks tool_call_id: type: string description: For tool messages refusal: type: string audio: type: object properties: id: type: string data: type: string expires_at: type: integer transcript: type: string reasoning: type: string reasoning_details: type: array items: type: object properties: id: type: string index: type: integer type: type: string enum: - reasoning.summary - reasoning.encrypted - reasoning.text summary: type: string text: type: string signature: type: string data: type: string annotations: type: array items: type: object properties: type: type: string url_citation: type: object properties: start_index: type: integer end_index: type: integer title: type: string url: type: string sources: type: object type: type: string tool_calls: type: array items: type: object required: - function properties: index: type: integer type: type: string id: type: string function: type: object properties: name: type: string arguments: type: string CacheControl: type: object description: Cache control settings for content blocks properties: type: type: string enum: - ephemeral ttl: type: string description: Time to live (e.g., "1m", "1h") AsyncJobStatus: type: string description: The status of an async job enum: - pending - processing - completed - failed ErrorField: type: object properties: type: type: string code: type: string message: type: string param: type: string event_id: type: string BifrostErrorExtraFields: type: object properties: provider: $ref: '#/components/schemas/ModelProvider' model_requested: type: string request_type: type: string ModelProvider: type: string description: AI model provider identifier enum: - openai - azure - anthropic - bedrock - cohere - vertex - vllm - mistral - ollama - groq - sgl - parasail - perplexity - replicate - cerebras - deepseek - gemini - openrouter - elevenlabs - huggingface - nebius - xai - runway - fireworks securitySchemes: BearerAuth: type: http scheme: bearer description: > Bearer token authentication. Use your provider API key or Bifrost authentication token. Virtual keys (prefixed with `sk-bf-`) can also be passed here. BasicAuth: type: http scheme: basic description: | Basic authentication using username and password. ApiKeyAuth: type: apiKey in: header name: x-api-key description: | API key authentication via the `x-api-key` header. Virtual keys (prefixed with `sk-bf-`) can also be passed here. VirtualKeyAuth: type: apiKey in: header name: x-bf-vk description: > Bifrost Virtual Key for governance, routing, and access control. Supported on all inference endpoints (`/v1/*`, `/openai/*`, `/anthropic/*`, `/bedrock/*`, `/cohere/*`, `/genai/*`, `/langchain/*`, `/litellm/*`, `/pydanticai/*`, `/mcp`), not on management APIs (`/api/*`). Example: `sk-bf-*` prefixed keys. ````