StreamLake

StreamLake Gateway API

The Gateway API from StreamLake — 1 operation(s) for gateway.

GitHub OpenAPI

Operations 1

POST /api/gateway/v1/endpoints/chat/completions Online Inference API Endpoint Conversation API #

Documentation

📖
Documentation
https://streamlake.ai/document/DOC/mj9z6fh8lxn87i86jrp

Specifications

⚙
OpenAPI
https://artifacts.apis.io/streamlake/openapi/streamlake-gateway-api-openapi.yml

Schemas & Data

📊
JSONSchema
https://artifacts.apis.io/streamlake/json-schema/streamlake-post-api-gateway-v1-endpoints-chat-completions-request-schema.json
📊
JSONSchema
https://artifacts.apis.io/streamlake/json-schema/streamlake-post-api-gateway-v1-endpoints-chat-completions-response-schema.json

Other Resources

🔗
ErrorCodes
https://streamlake.ai/document/DOC/mkf81ayc461ilb15zid
🔗
APIsJSON
https://artifacts.apis.io/streamlake/apis.yml

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.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/streamlake:streamlake-gateway-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

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.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

streamlake-gateway-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: StreamLake Gateway API
  version: '2026-10-13'
  description: 'GENERATED FROM DOCUMENTATION by API Evangelist on 2026-10-13: 3 operation(s) read from 2 public documentation page(s) (each operation names its page in x-source).'
  x-evidence-tiers:
    code-example: 2
    documentation: 1
    pages-with-code: 1
    pages-read: 2
  x-generated-from: documentation
  x-provenance: generated
  x-authored-by: API Evangelist
  x-generated: '2026-10-13'
  x-generator: generate-contract-from-docs.py
  x-engine: anthropic
  x-sources:
  - https://streamlake.ai/document/DOC/mj9z6fh8lxn87i86jrp
  - https://streamlake.ai/document/DOC/mg6k6nlp8j6qxicx4c9
servers:
- url: https://vanchin.streamlake.ai
security:
- bearer: []
tags:
- name: Gateway
paths:
  /api/gateway/v1/endpoints/chat/completions:
    post:
      operationId: post_api_gateway_v1_endpoints_chat_completions
      tags:
      - Gateway
      summary: Online Inference API Endpoint Conversation API
      x-source: https://streamlake.ai/document/DOC/mj9z6fh8lxn87i86jrp
      parameters:
      - name: model
        in: query
        required: true
        schema:
          type: string
        description: Inference Endpoint ID
      - name: temperature
        in: query
        required: false
        schema:
          type: number
        description: 'Sampling Temperature, Range: 0-2, Default: 1'
      - name: top_p
        in: query
        required: false
        schema:
          type: number
        description: 'Nucleus Sampling Parameter, Range: 0-1, Default: 1'
      - name: n
        in: query
        required: false
        schema:
          type: integer
        description: 'Number of Responses to Generate, Default: 1'
      - name: stream
        in: query
        required: false
        schema:
          type: boolean
        description: 'Whether to stream responses, Default: false'
      - name: stop
        in: query
        required: false
        schema:
          type: string
        description: Stop words
      - name: max_tokens
        in: query
        required: false
        schema:
          type: integer
        description: Maximum Generation Length
      - name: presence_penalty
        in: query
        required: false
        schema:
          type: number
        description: 'Presence Penalty, Range: -2 to 2, Default: 0'
      - name: frequency_penalty
        in: query
        required: false
        schema:
          type: number
        description: 'Frequency Penalty, Range: -2 to 2, Default: 0'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostApiGatewayV1EndpointsChatCompletionsRequest'
      responses:
        '200':
          description: Success (status as documented)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PostApiGatewayV1EndpointsChatCompletionsResponse'
      x-evidence:
        kind: documentation
components:
  schemas:
    PostApiGatewayV1EndpointsChatCompletionsRequest:
      type: object
      properties:
        model:
          type: string
          description: Inference Endpoint ID
        messages:
          type: array
          description: Lists of conversation messages
        temperature:
          type: number
          description: 'Sampling Temperature, Range: 0-2, Default: 1'
        top_p:
          type: number
          description: 'Nucleus Sampling Parameter, Range: 0-1, Default: 1'
        n:
          type: integer
          description: 'Number of Responses to Generate, Default: 1'
        stream:
          type: boolean
          description: 'Whether to stream responses, Default: false'
        stop:
          type: string
          description: Stop words
        max_tokens:
          type: integer
          description: Maximum Generation Length
        presence_penalty:
          type: number
          description: 'Presence Penalty, Range: -2 to 2, Default: 0'
        frequency_penalty:
          type: number
          description: 'Frequency Penalty, Range: -2 to 2, Default: 0'
      required:
      - model
      - messages
    PostApiGatewayV1EndpointsChatCompletionsResponse:
      type: object
      properties:
        id:
          type: string
          description: Request ID, uniquely identifies a single request
        object:
          type: string
          description: Object type, indicates this is a chat completion response
        created:
          type: integer
          description: Unix timestamp (in seconds) when this completion was created
        model:
          type: string
          description: Model name used to generate this completion
        choices:
          type: array
          description: A list of chat completion candidates generated by the model
        usage:
          type: object
          description: Token usage statistics
        service_tier:
          type: string
          description: Service tier (default/scale/etc.)
  securitySchemes:
    bearer:
      type: http
      scheme: bearer