Responses API

Haimaker supports the OpenAI Responses request format at POST /v1/responses for models whose catalog entry has mode: "responses".

Do not assume a chat model is also a Responses model. Query GET /public/model_hub and select a current model with mode: "responses".

from openai import OpenAI

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

response = client.responses.create(
    model="openai/gpt-5.5-pro",
    input="Explain why the sky is blue in two sentences.",
)

print(response.output_text)

curl https://api.haimaker.ai/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.5-pro",
    "input": "Explain why the sky is blue in two sentences."
  }'

Streaming is available by adding stream: true. Supported parameters remain model-specific and are listed in each model's supported_openai_params field in the public model catalog.