Prime Intellect

Prime Intellect Inference API

OpenAI-compatible inference API for hosted frontier and open models served at api.pinference.ai. Supports streaming chat completions, the full set of OpenAI parameters (temperature, top_p, max_tokens, logprobs), and returns a `usage` object with input/output token counts and USD cost on every response. LoRA adapters can be served alongside base models via 1-click deployments.

Prime Intellect Inference API is one of 6 APIs that Prime Intellect publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

This API exposes 1 machine-runnable capability that can be deployed as REST, MCP, or Agent Skill surfaces via Naftiko.

Tagged areas include Inference, OpenAI Compatible, Foundation Models, and LLM. The published artifact set on APIs.io includes API documentation, an OpenAPI specification, and 1 Naftiko capability spec.

GitHub OpenAPI

Documentation

📖
Documentation
https://docs.primeintellect.ai/inference/overview
📖
Documentation
https://docs.primeintellect.ai/inference/usage
📖
Documentation
https://docs.primeintellect.ai/inference/adapter-deployments

Specifications

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

Other Resources

🔗
NaftikoCapability
https://raw.githubusercontent.com/api-evangelist/prime-intellect/refs/heads/main/capabilities/inference-chat.yaml

OpenAPI Specification

prime-intellect-inference-api-openapi.yml Raw ↑ 
openapi: 3.1.0
info:
  title: Prime Intellect Inference API
  version: 1.0.0
  description: OpenAI-compatible inference API for hosted frontier and open models, served at api.pinference.ai. Supports
    streaming chat completions and model listing. Billed per million input/output tokens with usage metadata returned on each
    response.
  contact:
    name: Prime Intellect
    url: https://www.primeintellect.ai
servers:
- url: https://api.pinference.ai/api/v1
  description: Production Inference Server
security:
- HTTPBearer: []
tags:
- name: Inference
paths:
  /models:
    get:
      tags:
      - Inference
      summary: Prime Intellect List Inference Models
      description: List models available through the Prime Intellect inference API.
      operationId: listInferenceModels
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelList'
  /chat/completions:
    post:
      tags:
      - Inference
      summary: Prime Intellect Create Chat Completion
      description: OpenAI-compatible chat completions endpoint. Supports streaming, temperature, token limits, and logprobs.
        Responses include a usage object with input/output tokens and cost.
      operationId: createChatCompletion
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
components:
  securitySchemes:
    HTTPBearer:
      type: http
      scheme: bearer
  schemas:
    ModelList:
      type: object
      properties:
        object:
          type: string
          example: list
        data:
          type: array
          items:
            $ref: '#/components/schemas/Model'
    Model:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: model
        created:
          type: integer
        owned_by:
          type: string
    ChatMessage:
      type: object
      required:
      - role
      - content
      properties:
        role:
          type: string
          enum:
          - system
          - user
          - assistant
          - tool
        content:
          type: string
    ChatCompletionRequest:
      type: object
      required:
      - model
      - messages
      properties:
        model:
          type: string
        messages:
          type: array
          items:
            $ref: '#/components/schemas/ChatMessage'
        stream:
          type: boolean
          default: false
        temperature:
          type: number
        top_p:
          type: number
        max_tokens:
          type: integer
        logprobs:
          type: boolean
    Usage:
      type: object
      properties:
        prompt_tokens:
          type: integer
        completion_tokens:
          type: integer
        total_tokens:
          type: integer
        cost:
          type: number
    ChatCompletionChoice:
      type: object
      properties:
        index:
          type: integer
        message:
          $ref: '#/components/schemas/ChatMessage'
        finish_reason:
          type: string
    ChatCompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: chat.completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            $ref: '#/components/schemas/ChatCompletionChoice'
        usage:
          $ref: '#/components/schemas/Usage'