Qwen3.6 35B A3B

262 000 context
Vision
Reasoning

Model ID

Qwen/Qwen3.6-35B-A3B-FP8

Use It in Python

from openai import OpenAI

client = OpenAI(
    base_url="https://inference.hetzner.com/api/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3.6-35B-A3B-FP8",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Other free options: see every provider serving this model. Don't have a key yet? See how to get one — Hetzner Inference API asks for a payment card at sign-up.

Free Tier Limits (Hetzner Inference API)

Rate Limit
10 requests, 4 000 000 input / 100 000 output tokens per 60s (per API key)
Daily Limit
No daily cap published (free while the API is experimental); a Hetzner account with billing details is required and Hetzner may ask for a card or ID to verify it
Monthly Limit
Free during experimental phase, no billing system yet

More free models from Hetzner Inference API