Hyperbolic

Hyperbolic Completions API

Legacy OpenAI-compatible text completions endpoint for base-model prompting. Notably exposes Llama-3.1-405B-Base in both BF16 (high-throughput precision) and FP8 (low-latency) — Hyperbolic is the only public provider serving the base model in BF16.

Hyperbolic Completions API is one of 6 APIs that Hyperbolic 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 AI, Completions, Inference, 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.hyperbolic.ai/inference/overview

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/hyperbolic-ai/refs/heads/main/openapi/hyperbolic-completions-api-openapi.yml

Other Resources

🔗
NaftikoCapability
https://raw.githubusercontent.com/api-evangelist/hyperbolic-ai/refs/heads/main/capabilities/inference-completions.yaml

OpenAPI Specification

hyperbolic-completions-api-openapi.yml Raw ↑ 
openapi: 3.1.0
info:
  title: Hyperbolic Completions API
  description: >
    Legacy OpenAI-compatible text completions endpoint for prompting base
    (non-instruct) models. Hyperbolic is the only public provider serving
    `meta-llama/Meta-Llama-3.1-405B` (base) in BF16 for high-throughput
    precision and FP8 for ultra-low-latency.
  version: v1
  contact:
    name: Hyperbolic Support
    email: [email protected]
    url: https://docs.hyperbolic.ai
  license:
    name: Hyperbolic Terms of Use
    url: https://www.hyperbolic.ai/terms-of-use

servers:
  - url: https://api.hyperbolic.xyz/v1
    description: Hyperbolic Production Inference Server

security:
  - BearerAuth: []

tags:
  - name: Completions
    description: Legacy base-model text completion endpoint

paths:
  /completions:
    post:
      summary: Hyperbolic Create A Completion
      description: >
        Generate a text completion for a prompt against a base (non-instruct)
        model. Primarily used for the Llama-3.1-405B-Base BF16 and FP8 variants
        unique to Hyperbolic.
      operationId: createCompletion
      tags:
        - Completions
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CompletionRequest'
            examples:
              Base405B:
                summary: Llama-3.1-405B base BF16
                value:
                  model: meta-llama/Meta-Llama-3.1-405B
                  prompt: 'The three laws of robotics are:'
                  max_tokens: 256
                  temperature: 0.7
      responses:
        '200':
          description: Successful completion response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CompletionResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '429':
          description: Too Many Requests
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'

components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key

  schemas:
    CompletionRequest:
      type: object
      required:
        - model
        - prompt
      properties:
        model:
          type: string
          description: Base model ID (e.g. `meta-llama/Meta-Llama-3.1-405B`).
        prompt:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
        max_tokens:
          type: integer
          minimum: 1
        temperature:
          type: number
          minimum: 0
          maximum: 2
        top_p:
          type: number
          minimum: 0
          maximum: 1
        top_k:
          type: integer
        n:
          type: integer
          minimum: 1
        stream:
          type: boolean
        stop:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
        presence_penalty:
          type: number
        frequency_penalty:
          type: number
        seed:
          type: integer

    CompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          enum:
            - text_completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              index:
                type: integer
              text:
                type: string
              finish_reason:
                type: string
                enum:
                  - stop
                  - length
        usage:
          $ref: '#/components/schemas/Usage'

    Usage:
      type: object
      properties:
        prompt_tokens:
          type: integer
        completion_tokens:
          type: integer
        total_tokens:
          type: integer

    ErrorResponse:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
            code:
              type: string