WanAPIs Chat API
Chat completion endpoints (OpenAI Chat Completions compatible).
Chat completion endpoints (OpenAI Chat Completions compatible).
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
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.curl "https://apis.io/api/v1/apis/wanapis-chat-api"
curl "https://apis.io/api/v1/apis?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
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: 3.2.0
info:
title: WanAPIs Unified AI Chat API
version: '2026-05-27'
summary: OpenAI-compatible AI gateway aggregating GPT, Claude, Gemini, DeepSeek and other LLM, image, video, and audio model providers behind a single key.
description: 'WanAPIs (https://wanapis.com) is a developer-focused AI API gateway. Clients
issue OpenAI-style requests against `https://api.wanapis.com/v1`; the
platform routes them to the appropriate upstream model provider (OpenAI,
Anthropic, Google, DeepSeek, Moonshot, Alibaba, xAI, Mistral, Stability,
Midjourney, etc.) and applies per-project quota, metering, channel
routing, and failover.
This OpenAPI is **hand-authored** by API Evangelist. WanAPIs publishes no
machine-readable spec — `https://api.wanapis.com/openapi.json` returns the
admin dashboard. Operations included here are taken from
https://wanapis.com/docs and https://wanapis.com/pricing and reflect the
OpenAI-compatible surface plus the documented WanAPIs `/responses` and
async task patterns. Request and response schemas mirror the OpenAI HTTP
API by convention; consult the upstream OpenAI reference for full field
semantics.
'
termsOfService: https://wanapis.com/
contact:
name: WanAPIs Support
email: support@wanapis.com
url: https://wanapis.com/
license:
name: Proprietary
url: https://wanapis.com/
servers:
- url: https://api.wanapis.com/v1
description: WanAPIs production OpenAI-compatible base URL.
security:
- bearerAuth: []
tags:
- name: Chat
description: Chat completion endpoints (OpenAI Chat Completions compatible).
paths:
/chat/completions:
post:
tags:
- Chat
operationId: createChatCompletion
summary: Create a chat completion
description: 'OpenAI-compatible chat completions. Set `model` to any model slug
available in the WanAPIs marketplace (e.g. `claude-opus-4-7`,
`deepseek-v4-pro`, `gemini-3.5-flash`, `gpt-5.5`).
'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionRequest'
examples:
deepseek:
summary: DeepSeek chat completion
value:
model: deepseek-v4-pro
messages:
- role: user
content: 用三句话解释 RAG
responses:
'200':
description: Chat completion result.
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionResponse'
text/event-stream:
schema:
type: string
description: 'Server-Sent Events stream of `ChatCompletionChunk` objects when `stream: true`.'
'401':
$ref: '#/components/responses/Unauthorized'
'403':
$ref: '#/components/responses/Forbidden'
'429':
$ref: '#/components/responses/RateLimited'
'500':
$ref: '#/components/responses/UpstreamFailure'
components:
schemas:
Usage:
type: object
properties:
prompt_tokens:
type: integer
completion_tokens:
type: integer
total_tokens:
type: integer
ChatMessage:
type: object
required:
- role
- content
properties:
role:
type: string
enum:
- system
- user
- assistant
- tool
content:
oneOf:
- type: string
- type: array
items:
type: object
name:
type: string
tool_call_id:
type: string
tool_calls:
type: array
items:
type: object
ChatCompletionResponse:
type: object
properties:
id:
type: string
object:
type: string
const: chat.completion
created:
type: integer
model:
type: string
choices:
type: array
items:
type: object
properties:
index:
type: integer
message:
$ref: '#/components/schemas/ChatMessage'
finish_reason:
type: string
usage:
$ref: '#/components/schemas/Usage'
Error:
type: object
properties:
error:
type: object
properties:
message:
type: string
type:
type: string
code:
type: string
param:
type: string
nullable: true
ChatCompletionRequest:
type: object
required:
- model
- messages
properties:
model:
type: string
description: Marketplace model slug (e.g. claude-opus-4-7).
messages:
type: array
items:
$ref: '#/components/schemas/ChatMessage'
stream:
type: boolean
default: false
max_tokens:
type: integer
temperature:
type: number
minimum: 0
maximum: 2
top_p:
type: number
minimum: 0
maximum: 1
n:
type: integer
default: 1
stop:
oneOf:
- type: string
- type: array
items:
type: string
presence_penalty:
type: number
frequency_penalty:
type: number
seed:
type: integer
response_format:
type: object
tools:
type: array
items:
type: object
tool_choice:
oneOf:
- type: string
- type: object
user:
type: string
responses:
RateLimited:
description: Rate limit or quota exceeded.
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
Forbidden:
description: Key does not have access to the requested model or feature.
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
Unauthorized:
description: Missing or invalid API key.
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
UpstreamFailure:
description: Upstream provider failure (500–504). Retry with exponential backoff; WanAPIs may auto-failover to a configured channel.
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat: API Key
description: 'Authenticate every request with `Authorization: Bearer <wanapis_api_key>`.
Keys are issued per project in the WanAPIs dashboard and may be scoped
with quota and model availability.
'