> ## 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.

# Upstream OAuth proxy - authorize with upstream service

> Initiates an OAuth flow with an upstream MCP service (Notion, GitHub, etc.)
on behalf of the current user. Used during the consent flow (via "Connect" buttons
on the MCPs page) and at runtime when a tool call is made to an unauthenticated service.

**Consent flow** - provide `flow_id` (from the pending consent flow). The browser-binding
cookie (`__bifrost_flow_secret`) is validated.

**Runtime flow** - provide `session` (the Bifrost session ID from the token endpoint).
Used when a service was skipped during consent and needs to be connected later.

On success, redirects the user to the upstream provider's authorize URL. After the user
grants access, the upstream callback lands at `/api/oauth/callback`, stores the upstream
token against the user's identity, and redirects back to the consent screen (consent flow)
or returns an authorization success page (runtime flow).

Authentication is not required - cookie/session validation is performed instead.




## OpenAPI

````yaml /openapi/openapi.json get /api/oauth/per-user/upstream/authorize
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: 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
paths:
  /api/oauth/per-user/upstream/authorize:
    get:
      tags:
        - OAuth
        - Per-User OAuth
      summary: Upstream OAuth proxy - authorize with upstream service
      description: >
        Initiates an OAuth flow with an upstream MCP service (Notion, GitHub,
        etc.)

        on behalf of the current user. Used during the consent flow (via
        "Connect" buttons

        on the MCPs page) and at runtime when a tool call is made to an
        unauthenticated service.


        **Consent flow** - provide `flow_id` (from the pending consent flow).
        The browser-binding

        cookie (`__bifrost_flow_secret`) is validated.


        **Runtime flow** - provide `session` (the Bifrost session ID from the
        token endpoint).

        Used when a service was skipped during consent and needs to be connected
        later.


        On success, redirects the user to the upstream provider's authorize URL.
        After the user

        grants access, the upstream callback lands at `/api/oauth/callback`,
        stores the upstream

        token against the user's identity, and redirects back to the consent
        screen (consent flow)

        or returns an authorization success page (runtime flow).


        Authentication is not required - cookie/session validation is performed
        instead.
      operationId: authorizeUpstreamPerUserOAuth
      parameters:
        - name: mcp_client_id
          in: query
          required: true
          description: ID of the per-user OAuth MCP client to authenticate with
          schema:
            type: string
        - name: flow_id
          in: query
          required: false
          description: >
            Pending consent flow ID. Required if `session` is not provided.

            The `__bifrost_flow_secret` cookie must be present and match the
            flow.
          schema:
            type: string
        - name: session
          in: query
          required: false
          description: >
            Bifrost session ID (from the token endpoint). Required if `flow_id`
            is not provided.

            Used for runtime (post-consent) upstream authorization.
          schema:
            type: string
      responses:
        '302':
          description: Redirect to upstream OAuth provider's authorize URL
          headers:
            Location:
              schema:
                type: string
              description: Upstream provider authorization URL with PKCE parameters
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BifrostError'
        '401':
          description: Invalid or expired flow/session
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ManagementErrorResponse'
        '403':
          description: Browser-binding cookie mismatch (CSRF protection)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ManagementErrorResponse'
        '404':
          description: MCP client not found or not configured for per-user OAuth
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ManagementErrorResponse'
        '503':
          description: Config store is disabled
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ManagementErrorResponse'
components:
  schemas:
    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'
    ManagementErrorResponse:
      $ref: '#/components/schemas/BifrostError'
      type: object
      description: Error response
    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
        - 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.

````