Bifrost Chat API
Chat completions compatible with OpenAI chat API
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/bifrost-chat-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
title: Bifrost HTTP Gateway Chat API
description: The Bifrost HTTP Gateway API provides an OpenAI-compatible RESTful interface that routes requests to any of 20+ supported AI providers through a single unified endpoint. Requests specify the provider and model using the format provider/model-name in the model field, enabling seamless provider switching without client code changes.
version: v1
license:
name: Apache 2.0
url: https://www.apache.org/licenses/LICENSE-2.0
contact:
name: Bifrost Community
url: https://github.com/maximhq/bifrost
x-generated-from: documentation
servers:
- url: http://localhost:8080
description: Bifrost HTTP Gateway (default local port 8080)
tags:
- name: Chat
description: Chat completions compatible with OpenAI chat API
paths:
/v1/chat/completions:
post:
operationId: createChatCompletion
summary: Bifrost Create Chat Completion
description: Creates a chat completion routed to the specified AI provider and model. Use the format provider/model-name in the model field (e.g., openai/gpt-4o, anthropic/claude-3-5-sonnet-20241022).
tags:
- Chat
security:
- BifrostProviderAuth: []
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionRequest'
examples:
CreateChatCompletion201Example:
summary: Default createChatCompletion request example
x-microcks-default: true
value:
model: openai/gpt-4o
messages:
- role: user
content: Hello, how are you?
temperature: 0.7
max_tokens: 256
responses:
'200':
description: Chat completion response from the AI provider.
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionResponse'
examples:
CreateChatCompletion200Example:
summary: Default createChatCompletion 200 response
x-microcks-default: true
value:
id: chatcmpl-abc123
object: chat.completion
created: 1713000000
model: openai/gpt-4o
choices:
- index: 0
message:
role: assistant
content: Hello! I'm doing well, thank you for asking.
finish_reason: stop
usage:
prompt_tokens: 12
completion_tokens: 14
total_tokens: 26
'400':
description: Invalid request.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'502':
description: Upstream provider error.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
x-microcks-operation:
delay: 0
dispatcher: FALLBACK
/v1/chat/completions/stream:
post:
operationId: streamChatCompletion
summary: Bifrost Stream Chat Completion
description: Creates a streaming chat completion. Returns server-sent events (SSE) with incremental token chunks from the AI provider.
tags:
- Chat
security:
- BifrostProviderAuth: []
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionRequest'
examples:
StreamChatCompletion201Example:
summary: Default streamChatCompletion request example
x-microcks-default: true
value:
model: anthropic/claude-3-5-sonnet-20241022
messages:
- role: user
content: Tell me a short joke.
stream: true
responses:
'200':
description: Server-sent event stream of chat completion chunks.
content:
text/event-stream:
schema:
type: string
examples:
StreamChatCompletion200Example:
summary: Default streamChatCompletion 200 response
x-microcks-default: true
value: 'data: {"id":"chatcmpl-xyz","object":"chat.completion.chunk","choices":[{"delta":{"content":"Hello"},"index":0}]}
data: [DONE]
'
'400':
description: Invalid request.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
x-microcks-operation:
delay: 0
dispatcher: FALLBACK
components:
schemas:
ChatMessage:
title: Chat Message
description: A single message in a chat conversation.
type: object
required:
- role
- content
properties:
role:
type: string
description: Role of the message author.
enum:
- system
- user
- assistant
example: user
content:
type: string
description: Content of the message.
example: Hello, how are you?
ChatCompletionResponse:
title: Chat Completion Response
description: Response from a chat completion request.
type: object
properties:
id:
type: string
description: Unique identifier for the completion.
example: chatcmpl-abc123
object:
type: string
description: Object type, always chat.completion.
example: chat.completion
created:
type: integer
description: Unix timestamp of when the completion was created.
example: 1713000000
model:
type: string
description: Provider and model used for the completion.
example: openai/gpt-4o
choices:
type: array
description: Array of completion choices.
items:
$ref: '#/components/schemas/ChatChoice'
usage:
$ref: '#/components/schemas/UsageStats'
UsageStats:
title: Usage Stats
description: Token usage statistics for the completion.
type: object
properties:
prompt_tokens:
type: integer
description: Number of tokens in the prompt.
example: 12
completion_tokens:
type: integer
description: Number of tokens generated.
example: 14
total_tokens:
type: integer
description: Total tokens used.
example: 26
ChatCompletionRequest:
title: Chat Completion Request
description: Request body for creating a chat completion.
type: object
required:
- model
- messages
properties:
model:
type: string
description: Provider and model name in the format provider/model-name (e.g., openai/gpt-4o, anthropic/claude-3-5-sonnet-20241022).
example: openai/gpt-4o
messages:
type: array
description: Array of messages comprising the conversation.
items:
$ref: '#/components/schemas/ChatMessage'
temperature:
type: number
description: Sampling temperature between 0 and 2.
example: 0.7
max_tokens:
type: integer
description: Maximum number of tokens to generate.
example: 256
stream:
type: boolean
description: Whether to stream the response as SSE.
example: false
top_p:
type: number
description: Nucleus sampling probability.
example: 1.0
n:
type: integer
description: Number of completions to generate.
example: 1
ChatChoice:
title: Chat Choice
description: A single completion choice in the response.
type: object
properties:
index:
type: integer
description: Index of this choice.
example: 0
message:
$ref: '#/components/schemas/ChatMessage'
finish_reason:
type: string
description: Reason the generation stopped.
enum:
- stop
- length
- content_filter
example: stop
ErrorResponse:
title: Error Response
description: Standard error response.
type: object
properties:
error:
type: string
description: Error message.
example: invalid model format
code:
type: integer
description: HTTP status code.
example: 400
securitySchemes:
BifrostProviderAuth:
type: apiKey
in: header
name: x-bf-provider-key
description: Provider API key passed as x-bf-provider-key header. Alternatively, provider keys can be configured server-side in bifrost configuration.