Float16 API

openapi: 3.1.0
info:
  title: Float16 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
paths:
  /fact:
    get:
      operationId: get_fact
      tags:
      - Fact
      summary: GET /fact
      x-source: https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/install-new-library.md
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: python
        snippet: requests.get('https://catfact.ninja/fact')
  /task/run/function/x7x2DFl8zU/hello:
    get:
      operationId: get_task_run_function_x7x2DFl8zU_hello
      tags:
      - Task
      summary: GET /task/run/function/x7x2DFl8zU/hello
      x-source: https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/server-mode.md
      responses:
        '200':
          description: Success (shape read from the example response on the page)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetTaskRunFunctionX7X2Dfl8ZuHelloResponse'
      x-evidence:
        kind: code-example
        language: curl
        snippet: 'curl -X GET "http://api.float16.cloud/task/run/function/x7x2DFl8zU/hello" -H "Authorization: Bearer float16-r-QoZU7uNlgDIFJ5IMrBtOCjuzVBlC"

          </code></pre>'
  /task/run/server/x7x2DFl8zU/chat:
    post:
      operationId: post_task_run_server_x7x2DFl8zU_chat
      tags:
      - Task
      summary: POST /task/run/server/x7x2DFl8zU/chat
      x-source: https://docs.float16.cloud/getting-started/serverless-gpu/tutorials/llm-dynamic-batching.md
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostTaskRunServerX7X2Dfl8ZuChatRequest'
      responses:
        '201':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: curl
        snippet: 'curl -X POST "http://api.float16.cloud/task/run/server/x7x2DFl8zU/chat" -H "Authorization: Bearer float16-r-QoZU7uNlgDIFJ5IMrBtOCjuzVBlC"
          -d ''{ "messages": "Hi !! Who are you ?" }'' &'
  /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
  /v1/ocr/extract:
    post:
      operationId: post_v1_ocr_extract
      tags:
      - Ocr
      summary: POST /v1/ocr/extract
      x-source: https://float16.cloud/en-en/docs/getting-started/quick-start
      responses:
        '201':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: curl
        snippet: "curl -X POST https://api.float16.cloud/v1/ocr/extract  -H \"Authorization: Bearer YOUR_API_KEY\"  -F \"file=@document.pdf\"\
          \ \n OCR Documentation \n Train with ML Frameworks \n Launch a pre-configured training environment: \n Navigate to Instances > Create\
          \ \n Select a framework image:\n float16/tao:6.0 - Computer vision \n float16/monai:1.5.1 - Medical imaging \n float16/nemo:2.6.1 -\
          \ Speech/NLP \n Choose your G"
  /{instanceid}/{id}/v1:
    get:
      operationId: get_instanceid_id_v1
      tags:
      - Api
      summary: GET /{instanceId}/{id}/v1
      x-source: https://float16.cloud/en-en/docs/ai-services/vllm-playground
      parameters:
      - name: instanceid
        in: path
        required: true
        schema:
          type: string
      - name: id
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Success (shape read from the example response on the page)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetInstanceidIdV1Response'
      x-evidence:
        kind: code-example
        language: curl
        snippet: "curl, JSON) \n Message Input : Type messages (Shift+Enter for new line) \n Clear Chat : Reset the conversation \n Tool Calling\
          \ \n Test function calling with pre-configured example tools. \n Enabling Tool Calling \n Toggle Tool Calling to ON in Settings \n Select\
          \ Tool Choice :\n Auto : Model decides when to use tools \n Required : Model must use a tool \n None : Disable tool usage \n Available\
          \ Tools \n The Pla"
  /{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:
    GetTaskRunFunctionX7X2Dfl8ZuHelloResponse:
      type: object
      properties:
        message:
          type: string
    PostTaskRunServerX7X2Dfl8ZuChatRequest:
      type: object
      properties:
        messages:
          type: string
    PostV1ChatRequest:
      type: object
      properties:
        model:
          type: string
        messages:
          type: array
          items:
            type: object
            properties:
              role:
                type: string
              content:
                type: string
    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
    GetInstanceidIdV1Response:
      type: object
      properties:
        role:
          type: string
        content:
          type: string
    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
  securitySchemes:
    bearer:
      type: http
      scheme: bearer
security:
- bearer: []
tags:
- name: Api
- name: Chat
- name: Fact
- name: Ocr
- name: Task