Float16

Float16 Chat API

The Chat API from Float16 — 3 operation(s) for chat.

Documentation GitHub OpenAPI

Operations 3

POST /v1/chat POST /v1/chat #

POST /v1/chat/completions POST /v1/chat/completions #

POST /{instanceid}/{id}/v1/chat/completions POST /{instanceId}/{id}/v1/chat/completions #

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/float16:float16-chat-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

openapi: 3.2.0
info:
  title: Float16 Chat API
  version: '2026-10-16'
  description: 'GENERATED FROM DOCUMENTATION by API Evangelist on 2026-10-16: 8 operation(s) read from 16 public documentation page(s) (each operation names its page in x-source). This is not the provider''s published contract; Float16 has published no machine-readable contract that the pipeline could find. Engine: local.'
  x-evidence-tiers:
    code-example: 8
    documentation: 0
    pages-with-code: 16
    pages-read: 16
  x-generated-from: documentation
  x-provenance: generated
  x-authored-by: API Evangelist
  x-generated: '2026-10-16'
  x-generator: generate-contract-from-docs.py
  x-engine: local
  x-sources:
  - https://float16.cloud/en-en/docs/api-reference
  - https://float16.cloud/en-en/docs/api-reference/overview
  - https://float16.cloud/en-en/docs/api-reference/chat-completions
  - https://float16.cloud/en-en/solutions/software-developer
  - https://float16.cloud/en-en/docs/getting-started/quick-start
  - https://docs.float16.cloud/getting-started/llm-as-a-service/quick-start.md
  - https://docs.float16.cloud/getting-started/one-click-deploy/quick-start.md
  - https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/server-mode.md
  - https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/install-new-library.md
  - https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/llm-dynamic-batching.md
  - https://float16.cloud/en-en/docs/ai-services/llm-deployment
  - https://float16.cloud/en-en/docs/ai-services/vllm-playground
  - https://float16.cloud/en-en/docs/ai-services/typhoon-ocr
  - https://docs.float16.cloud/getting-started/one-click-deploy/quick-start
  - https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/server-mode
  - https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/llm-dynamic-batching
servers:
- url: https://proxy-instance.float16.cloud
security:
- bearer: []
tags:
- name: Chat
paths:
  /v1/chat:
    post:
      operationId: post_v1_chat
      tags:
      - Chat
      summary: POST /v1/chat
      x-source: https://float16.cloud/en-en/solutions/software-developer
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostV1ChatRequest'
      responses:
        '201':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: javascript
        snippet: "fetch('https://api.float16.cloud/v1/chat', {\n method: 'POST',\n headers: {\n 'Content-Type': 'application/json',\n 'X-API-Key': 'pk_your_protected_key'\n },\n body: JSON.stringify({\n model: 'typhoon-v2-70b-instruct',\n messages: [{ role: 'user', content: 'Hello!' }]\n })"
  /v1/chat/completions:
    post:
      operationId: post_v1_chat_completions
      tags:
      - Chat
      summary: POST /v1/chat/completions
      description: Live example of posting chat completions to the Float16 API.
      x-source: https://float16.cloud/en-en/solutions/software-developer
      parameters:
      - name: X-API-Key
        in: header
        required: true
        schema:
          type: string
        description: API key for authentication
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostV1ChatCompletionsRequest'
      responses:
        '201':
          description: Success (status as documented)
      x-evidence:
        kind: documentation
  /{instanceid}/{id}/v1/chat/completions:
    post:
      operationId: post_instanceid_id_v1_chat_completions
      tags:
      - Chat
      summary: POST /{instanceId}/{id}/v1/chat/completions
      x-source: https://float16.cloud/en-en/docs/api-reference
      parameters:
      - name: instanceid
        in: path
        required: true
        schema:
          type: string
      - name: id
        in: path
        required: true
        schema:
          type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostInstanceidIdV1ChatCompletionsRequest'
      responses:
        '201':
          description: Success (shape read from the example response on the page)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PostInstanceidIdV1ChatCompletionsResponse'
      x-evidence:
        kind: code-example
        language: curl
        snippet: "curl -X POST \"https://proxy-instance.float16.cloud/{instance_id}/3900/v1/chat/completions\"  -H \"Content-Type: application/json\"  -d '{ \n \"model\": \"your-model-name\", \n \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}] \n }' \n JavaScript \n import OpenAI from 'openai' ; \n const client = new OpenAI ({ \n apiKey : 'not-needed' , \n baseURL : 'https://proxy-instance.float16.cloud/{instance_id}/3900/v1' \n"
components:
  schemas:
    PostV1ChatCompletionsRequest:
      type: object
      properties:
        model:
          type: string
          description: The model to use, e.g., 'typhoon-v2-70b-instruct'
        messages:
          type: array
          description: List of message objects
        messages[].role:
          type: string
          description: Role of the message sender (e.g., 'user')
        messages[].content:
          type: string
          description: Content of the message
      required:
      - model
      - messages
      - messages[].role
      - messages[].content
    PostInstanceidIdV1ChatCompletionsRequest:
      type: object
      properties:
        model:
          type: string
        messages:
          type: array
          items:
            type: object
            properties:
              role:
                type: string
              content:
                type: string
    PostInstanceidIdV1ChatCompletionsResponse:
      type: object
      properties:
        model:
          type: string
        messages:
          type: array
          items:
            type: object
            properties:
              role:
                type: string
              content:
                type: string
    PostV1ChatRequest:
      type: object
      properties:
        model:
          type: string
        messages:
          type: array
          items:
            type: object
            properties:
              role:
                type: string
              content:
                type: string
  securitySchemes:
    bearer:
      type: http
      scheme: bearer