> ## 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. # Compact context (OpenAI) > Compresses a conversation into an opaque compaction item using the OpenAI-compatible `/v1/responses/compact` endpoint. Drop-in compatible with the OpenAI SDK. The response `output` contains the user messages plus a final item with `type: "response.compaction"` and `encrypted_content`. Pass this output as `input` to future Responses API calls to continue the conversation using the compacted context. **Note:** This endpoint also works without the `/v1` prefix (e.g., `/openai/responses/compact`). ## OpenAPI ````yaml /openapi/openapi.json post /openai/v1/responses/compact 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: /openai/v1/responses/compact: post: tags: - OpenAI Integration summary: Compact context (OpenAI) description: > Compresses a conversation into an opaque compaction item using the OpenAI-compatible `/v1/responses/compact` endpoint. Drop-in compatible with the OpenAI SDK. The response `output` contains the user messages plus a final item with `type: "response.compaction"` and `encrypted_content`. Pass this output as `input` to future Responses API calls to continue the conversation using the compacted context. **Note:** This endpoint also works without the `/v1` prefix (e.g., `/openai/responses/compact`). operationId: openaiCreateCompaction requestBody: required: true content: application/json: schema: type: object required: - model properties: model: type: string description: > Model identifier (e.g., "gpt-4o"). When routing through Bifrost's provider-prefixed path, use "provider/model" format. input: oneOf: - type: string - type: array items: type: object properties: id: type: string type: type: string enum: - message - file_search_call - computer_call - computer_call_output - web_search_call - web_fetch_call - function_call - function_call_output - code_interpreter_call - local_shell_call - local_shell_call_output - mcp_call - custom_tool_call - custom_tool_call_output - image_generation_call - mcp_list_tools - mcp_approval_request - mcp_approval_responses - reasoning - item_reference - refusal status: type: string enum: - in_progress - completed - incomplete - interpreting - failed role: type: string enum: - assistant - user - system - developer content: oneOf: - type: string - type: array items: type: object required: - type properties: type: type: string enum: - input_text - input_image - input_file - input_audio - output_text - refusal - reasoning_text file_id: type: string text: type: string signature: type: string image_url: type: string detail: type: string file_data: type: string file_url: type: string filename: type: string file_type: type: string input_audio: type: object required: - format - data properties: format: type: string enum: - mp3 - wav data: type: string annotations: type: array items: type: object properties: type: type: string enum: - file_citation - url_citation - container_file_citation - file_path index: type: integer file_id: type: string text: type: string start_index: type: integer end_index: type: integer filename: type: string title: type: string url: type: string container_id: type: string logprobs: type: array items: type: object properties: bytes: type: array items: type: integer logprob: type: number token: type: string top_logprobs: type: array items: type: object properties: bytes: type: array items: type: integer logprob: type: number token: type: string refusal: type: string cache_control: $ref: '#/components/schemas/CacheControl' call_id: type: string name: type: string arguments: type: string output: description: > Tool call output. A plain string for function/custom/local-shell tool outputs, an array of content blocks for structured function tool outputs, or a computer-tool screenshot object for computer_call_output. oneOf: - type: string - type: array items: type: object required: - type properties: type: type: string enum: - input_text - input_image - input_file - input_audio - output_text - refusal - reasoning_text file_id: type: string text: type: string signature: type: string image_url: type: string detail: type: string file_data: type: string file_url: type: string filename: type: string file_type: type: string input_audio: type: object required: - format - data properties: format: type: string enum: - mp3 - wav data: type: string annotations: type: array items: type: object properties: type: type: string enum: - file_citation - url_citation - container_file_citation - file_path index: type: integer file_id: type: string text: type: string start_index: type: integer end_index: type: integer filename: type: string title: type: string url: type: string container_id: type: string logprobs: type: array items: type: object properties: bytes: type: array items: type: integer logprob: type: number token: type: string top_logprobs: type: array items: type: object properties: bytes: type: array items: type: integer logprob: type: number token: type: string refusal: type: string cache_control: $ref: '#/components/schemas/CacheControl' - type: object description: >- Computer tool call output (computer_screenshot). properties: type: type: string enum: - computer_screenshot file_id: type: string image_url: type: string action: type: object error: type: string queries: type: array items: type: string results: type: array items: type: object summary: type: array items: type: object required: - type - text properties: type: type: string enum: - summary_text text: type: string encrypted_content: type: string description: > Conversation to compact. Required unless previous_response_id is set. Compaction items (type "response.compaction") from prior responses may be included. instructions: type: string description: >- System instructions that persist across the compacted context. previous_response_id: type: string description: >- ID of a previous response to extend rather than sending full input. prompt_cache_key: type: string prompt_cache_retention: type: string service_tier: type: string fallbacks: type: array items: type: string description: >- Bifrost-specific — fallback model list in provider/model format. responses: '200': description: Successful compaction response content: application/json: schema: type: object properties: id: type: string object: type: string description: Always "response.compaction" example: response.compaction model: type: string created_at: type: integer output: type: array items: type: object properties: id: type: string type: type: string enum: - message - file_search_call - computer_call - computer_call_output - web_search_call - web_fetch_call - function_call - function_call_output - code_interpreter_call - local_shell_call - local_shell_call_output - mcp_call - custom_tool_call - custom_tool_call_output - image_generation_call - mcp_list_tools - mcp_approval_request - mcp_approval_responses - reasoning - item_reference - refusal status: type: string enum: - in_progress - completed - incomplete - interpreting - failed role: type: string enum: - assistant - user - system - developer content: oneOf: - type: string - type: array items: type: object required: - type properties: type: type: string enum: - input_text - input_image - input_file - input_audio - output_text - refusal - reasoning_text file_id: type: string text: type: string signature: type: string image_url: type: string detail: type: string file_data: type: string file_url: type: string filename: type: string file_type: type: string input_audio: type: object required: - format - data properties: format: type: string enum: - mp3 - wav data: type: string annotations: type: array items: type: object properties: type: type: string enum: - file_citation - url_citation - container_file_citation - file_path index: type: integer file_id: type: string text: type: string start_index: type: integer end_index: type: integer filename: type: string title: type: string url: type: string container_id: type: string logprobs: type: array items: type: object properties: bytes: type: array items: type: integer logprob: type: number token: type: string top_logprobs: type: array items: type: object properties: bytes: type: array items: type: integer logprob: type: number token: type: string refusal: type: string cache_control: $ref: '#/components/schemas/CacheControl' call_id: type: string name: type: string arguments: type: string output: description: > Tool call output. A plain string for function/custom/local-shell tool outputs, an array of content blocks for structured function tool outputs, or a computer-tool screenshot object for computer_call_output. oneOf: - type: string - type: array items: type: object required: - type properties: type: type: string enum: - input_text - input_image - input_file - input_audio - output_text - refusal - reasoning_text file_id: type: string text: type: string signature: type: string image_url: type: string detail: type: string file_data: type: string file_url: type: string filename: type: string file_type: type: string input_audio: type: object required: - format - data properties: format: type: string enum: - mp3 - wav data: type: string annotations: type: array items: type: object properties: type: type: string enum: - file_citation - url_citation - container_file_citation - file_path index: type: integer file_id: type: string text: type: string start_index: type: integer end_index: type: integer filename: type: string title: type: string url: type: string container_id: type: string logprobs: type: array items: type: object properties: bytes: type: array items: type: integer logprob: type: number token: type: string top_logprobs: type: array items: type: object properties: bytes: type: array items: type: integer logprob: type: number token: type: string refusal: type: string cache_control: $ref: '#/components/schemas/CacheControl' - type: object description: Computer tool call output (computer_screenshot). properties: type: type: string enum: - computer_screenshot file_id: type: string image_url: type: string action: type: object error: type: string queries: type: array items: type: string results: type: array items: type: object summary: type: array items: type: object required: - type - text properties: type: type: string enum: - summary_text text: type: string encrypted_content: type: string description: > The compacted output — the original user messages plus a final item of type "response.compaction" whose encrypted_content holds the opaque compacted state. Pass the full output array as input to a future Responses API request. usage: type: object properties: input_tokens: type: integer input_tokens_details: type: object properties: text_tokens: type: integer audio_tokens: type: integer image_tokens: type: integer cached_read_tokens: type: integer description: > Tokens served from the prompt cache (cache hit), billed at the reduced cache-read rate. Already included in the parent input_tokens total. cached_write_tokens: type: integer description: > Tokens written to the prompt cache on this request, billed at the cache-creation rate. Already included in the parent input_tokens total. Populated for providers that separately report cache write tokens (Anthropic, Bedrock). output_tokens: type: integer output_tokens_details: type: object properties: text_tokens: type: integer accepted_prediction_tokens: type: integer audio_tokens: type: integer reasoning_tokens: type: integer rejected_prediction_tokens: type: integer citation_tokens: type: integer num_search_queries: type: integer total_tokens: type: integer cost: $ref: '#/components/schemas/BifrostCost' extra_fields: $ref: '#/components/schemas/BifrostResponseExtraFields' '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: schemas: 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") BifrostCost: type: object description: Cost breakdown for the request properties: input_tokens_cost: type: number output_tokens_cost: type: number reasoning_tokens_cost: type: number description: Cost for reasoning/thinking tokens (reasoning models) citation_tokens_cost: type: number description: Cost for citation tokens search_queries_cost: type: number description: Cost for web search queries request_cost: type: number total_cost: type: number BifrostResponseExtraFields: type: object description: Additional fields included in responses properties: request_type: type: string description: Type of request that was made provider: $ref: '#/components/schemas/ModelProvider' model_requested: type: string description: The model that was requested model_deployment: type: string description: The actual model deployment used latency: type: integer format: int64 description: Request latency in milliseconds chunk_index: type: integer description: Index of the chunk for streaming responses raw_request: type: object description: Raw request if enabled raw_response: type: object description: Raw response if enabled cache_debug: $ref: '#/components/schemas/BifrostCacheDebug' 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' 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 BifrostCacheDebug: type: object properties: cache_hit: type: boolean cache_id: type: string hit_type: type: string requested_provider: type: string requested_model: type: string provider_used: type: string model_used: type: string input_tokens: type: integer threshold: type: number similarity: type: number 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 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. ````