Haimaker API

Haimaker is a hosted, unified API for the models enabled in our production catalog. Use your Haimaker API key with an OpenAI-compatible client, the Anthropic Messages protocol, or Gemini generateContent.

The model catalog changes independently of the docs. Query GET /public/model_hub for the current model names, prices, capabilities, and providers.

Chat Completions quick start

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

curl https://api.haimaker.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Public inference protocols

Protocol	Endpoint
OpenAI Chat Completions	POST /v1/chat/completions
OpenAI Responses	POST /v1/responses
Anthropic Messages	POST /v1/messages
Gemini generateContent	POST /v1beta/models/{model}:generateContent

These are the public inference surfaces Haimaker documents. The upstream proxy code contains other endpoint implementations, but their presence in the repository does not make them part of the Haimaker product.

Use the filtered GET /openapi.json schema for a machine-readable version of this contract.

Authentication

Send your API key as a bearer token:

Authorization: Bearer YOUR_API_KEY

Create and manage keys in the Haimaker dashboard or through the Key Management API.