Taalas

Taalas API

Taalas-native REST interface for running inference against the HC1 hardcore-model silicon. Three operations: a public /health probe reporting server status, queue depth and the currently loaded LoRA adapter; /models for model information; and /generate, the Taalas-native text-generation operation supporting streaming, tool calling, guided JSON/regex generation, logprobs and stop sequences. Authenticated with a bearer API key; only /health is reachable anonymously.

GitHub OpenAPI

Operations 3

POST /generate Generate #
POST /completions Completions #
POST /chat/completions Chat Completions #

Documentation

📖
Documentation
https://api.taalas.com/docs
📖
APIReference
https://api.taalas.com/docs
📖
Authentication
https://raw.githubusercontent.com/api-evangelist/taalas/refs/heads/main/authentication/taalas-authentication.yml

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/taalas/refs/heads/main/openapi/taalas-inference-api-openapi.yml

Other Resources

🔗
Conventions
https://raw.githubusercontent.com/api-evangelist/taalas/refs/heads/main/conventions/taalas-conventions.yml
🔗
ErrorCatalog
https://raw.githubusercontent.com/api-evangelist/taalas/refs/heads/main/errors/taalas-problem-types.yml
🔗
DataModel
https://raw.githubusercontent.com/api-evangelist/taalas/refs/heads/main/data-model/taalas-data-model.yml
🔗
Overlay
https://raw.githubusercontent.com/api-evangelist/taalas/refs/heads/main/overlays/taalas-inference-api-overlay.yaml
🔗
APIsJSON
https://raw.githubusercontent.com/api-evangelist/taalas/refs/heads/main/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/taalas-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.

GitHub Google LinkedIn

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

OpenAPI Specification

taalas-inference-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Taalas Inference API
  version: 1.0.0
  description: 'Operations tagged Inference across 2 of this provider''s published API definitions: taalas-inference-api-openapi.yml, taalas-inference-v1-api-openapi.yml. Each path carries the servers of the definition it was published in.'
servers:
- url: https://api.taalas.com
  description: Base URL declared by the provider in apis.yml (roadmap#122).
- url: /v1
tags:
- name: Inference
paths:
  /generate:
    post:
      tags:
      - Inference
      summary: Generate
      description: Generate text based on the input prompt.
      operationId: generate_generate_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GenerateRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    servers:
    - url: https://api.taalas.com
      description: Base URL declared by the provider in apis.yml (roadmap#122).
  /completions:
    post:
      tags:
      - Inference
      summary: Completions
      description: Generate text based on the input prompt.
      operationId: completions_completions_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/V1CompletionsRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    servers:
    - url: /v1
  /chat/completions:
    post:
      tags:
      - Inference
      summary: Chat Completions
      description: Generate text based on the input prompt.
      operationId: chat_completions_chat_completions_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/V1ChatCompletionsRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    servers:
    - url: /v1
components:
  schemas:
    StreamOptions:
      properties:
        include_usage:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Include Usage
          default: false
        include_obfuscation:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Include Obfuscation
          default: false
      type: object
      title: StreamOptions
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    GenerateRequest:
      properties:
        prompt:
          items:
            type: object
          type: array
          title: Prompt
          description: The input prompt for the language model to generate text from.
        min_output_tokens:
          type: integer
          minimum: 0.0
          title: Min Output Tokens
          description: Minimum number of tokens to output.
          default: 0
        max_output_tokens:
          type: integer
          minimum: 0.0
          title: Max Output Tokens
          description: Maximum number of tokens to output.
          default: 0
        topk:
          type: integer
          maximum: 8.0
          minimum: 1.0
          title: Topk
          description: Choose top k tokens.
          default: 1
        model:
          type: string
          title: Model
          description: The name of the model or adapter to use for generation.
          default: llama3.1-8B
        stream:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Stream
          description: Whether to stream the response back incrementally.
          default: false
        tools:
          anyOf:
          - items:
              type: object
            type: array
          - type: 'null'
          title: Tools
          description: List of tools given to model.
        tool_choice:
          anyOf:
          - type: string
          - type: 'null'
          title: Tool Choice
          description: Controls which (if any) tool is called by the model.
        logprobs:
          type: boolean
          title: Logprobs
          description: Whether to return log probabilities of the output tokens or not.
          default: false
        top_logprobs:
          type: integer
          maximum: 20.0
          minimum: 0.0
          title: Top Logprobs
          description: Return output tokens with top probabilities.
          default: 0
        system_prompt_version:
          type: string
          title: System Prompt Version
          description: Which system prompt to use in the backend.
          default: offline
        tool_name:
          type: string
          title: Tool Name
          description: Which tool was selected by router LLM model.
          default: ''
        context_for_tool:
          type: string
          title: Context For Tool
          description: Context most relavant to selected tool.
          default: ''
        guided_json:
          anyOf:
          - type: object
          - type: 'null'
          title: Guided Json
          description: A JSON schema for guided generation.
        guided_regex:
          anyOf:
          - type: string
          - type: 'null'
          title: Guided Regex
          description: A regex pattern for guided generation.
        response_format:
          anyOf:
          - type: object
          - type: 'null'
          title: Response Format
          description: For JSON object output.
        metadata:
          anyOf:
          - type: object
          - type: 'null'
          title: Metadata
          description: Used to propagate number of prefill and decode tokens.
        echo:
          type: boolean
          title: Echo
          description: Echo back the prompt in addition to the completion.
          default: false
        stream_options:
          anyOf:
          - $ref: '#/components/schemas/StreamOptions'
          - type: 'null'
          description: 'If stream: true, this will cause the server to send back usage stats as a final chunk.'
        stop:
          anyOf:
          - items:
              type: string
            type: array
          - type: string
          - type: 'null'
          title: Stop
          description: Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
        temperature:
          anyOf:
          - type: number
            maximum: 2.0
            minimum: 0.0
          - type: 'null'
          title: Temperature
          description: What sampling temperature to use, between 0 and 2.
          default: 1
        ignore_eos:
          type: boolean
          title: Ignore Eos
          description: Ignore end of sequence (stop_id) and continue generation until output limit is hit.
          default: false
      additionalProperties: true
      type: object
      required:
      - prompt
      title: GenerateRequest
    ParametersDefinition:
      properties:
        type:
          type: string
          title: Type
          default: object
        description:
          type: string
          title: Description
          default: ''
        properties:
          anyOf:
          - type: object
          - type: 'null'
          title: Properties
        required:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Required
      type: object
      title: ParametersDefinition
    FunctionDefinition:
      properties:
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
        parameters:
          anyOf:
          - $ref: '#/components/schemas/ParametersDefinition'
          - type: 'null'
      type: object
      title: FunctionDefinition
    V1CompletionsRequest:
      properties:
        model:
          type: string
          title: Model
        prompt:
          anyOf:
          - type: string
          - items:
              type: string
            type: array
          - items:
              type: integer
            type: array
          - items:
              items:
                type: integer
              type: array
            type: array
          title: Prompt
        stream:
          type: boolean
          title: Stream
          default: false
        echo:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Echo
          default: false
        max_tokens:
          type: integer
          minimum: 0.0
          title: Max Tokens
          default: 0
        stream_options:
          anyOf:
          - $ref: '#/components/schemas/StreamOptions'
          - type: 'null'
        logprobs:
          anyOf:
          - type: integer
            maximum: 5.0
            minimum: 0.0
          - type: 'null'
          title: Logprobs
        temperature:
          type: number
          maximum: 2.0
          minimum: 0.0
          title: Temperature
          default: 1
        stop:
          anyOf:
          - items:
              type: string
            type: array
          - type: string
          - type: 'null'
          title: Stop
        top_p:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Top P
          default: 1.0
        ignore_eos:
          type: boolean
          title: Ignore Eos
          default: false
      additionalProperties: true
      type: object
      required:
      - model
      - prompt
      title: V1CompletionsRequest
    ImageContent:
      properties:
        type:
          type: string
          title: Type
          default: image_url
        image_url:
          additionalProperties:
            type: string
          type: object
          title: Image Url
      type: object
      required:
      - image_url
      title: ImageContent
    TextContent:
      properties:
        type:
          type: string
          title: Type
          default: text
        text:
          type: string
          title: Text
      type: object
      required:
      - text
      title: TextContent
    Message:
      properties:
        role:
          type: string
          title: Role
        content:
          anyOf:
          - type: string
          - items:
              anyOf:
              - $ref: '#/components/schemas/TextContent'
              - $ref: '#/components/schemas/ImageContent'
              - type: object
            type: array
          title: Content
      type: object
      required:
      - role
      title: Message
    Tool:
      properties:
        type:
          type: string
          title: Type
          default: function
        function:
          anyOf:
          - $ref: '#/components/schemas/FunctionDefinition'
          - type: 'null'
      type: object
      title: Tool
    V1ChatCompletionsRequest:
      properties:
        model:
          type: string
          title: Model
        messages:
          items:
            $ref: '#/components/schemas/Message'
          type: array
          title: Messages
        temperature:
          type: number
          maximum: 2.0
          minimum: 0.0
          title: Temperature
          default: 1
        top_p:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Top P
          default: 1
        n:
          anyOf:
          - type: integer
            minimum: 1.0
          - type: 'null'
          title: N
          default: 1
        stream:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Stream
          default: false
        stop:
          anyOf:
          - items:
              type: string
            type: array
          - type: string
          - type: 'null'
          title: Stop
        max_tokens:
          anyOf:
          - type: integer
            minimum: 0.0
          - type: 'null'
          title: Max Tokens
          default: 0
        max_completion_tokens:
          anyOf:
          - type: integer
            minimum: 0.0
          - type: 'null'
          title: Max Completion Tokens
          default: 0
        presence_penalty:
          anyOf:
          - type: number
            maximum: 2.0
            minimum: -2.0
          - type: 'null'
          title: Presence Penalty
        frequency_penalty:
          anyOf:
          - type: number
            maximum: 2.0
            minimum: -2.0
          - type: 'null'
          title: Frequency Penalty
        logit_bias:
          anyOf:
          - additionalProperties:
              type: number
            type: object
          - type: 'null'
          title: Logit Bias
        user:
          anyOf:
          - type: string
          - type: 'null'
          title: User
        tools:
          anyOf:
          - items:
              $ref: '#/components/schemas/Tool'
            type: array
          - type: 'null'
          title: Tools
        tool_choice:
          anyOf:
          - type: string
          - type: 'null'
          title: Tool Choice
        logprobs:
          type: boolean
          title: Logprobs
          default: false
        top_logprobs:
          type: integer
          maximum: 20.0
          minimum: 0.0
          title: Top Logprobs
          default: 0
        stream_options:
          anyOf:
          - $ref: '#/components/schemas/StreamOptions'
          - type: 'null'
        ignore_eos:
          type: boolean
          title: Ignore Eos
          default: false
      additionalProperties: true
      type: object
      required:
      - model
      title: V1ChatCompletionsRequest
x-refined-from:
- taalas-inference-api-openapi.yml
- taalas-inference-v1-api-openapi.yml