router.fabryka.ai

One API for qwen3.6-35b-a3b

OpenAI-compatible inference. Sign up with your email and get $100 of free credit — no card, no waiting.

Already have a key? Check your balance → · API docs → · Hermes →

How to integrate

Any OpenAI-compatible client — set three things:

base url https://router.fabryka.ai/v1
api key sk-fab-… (from signup above)
model qwen3.6-35b-a3b

curl

curl https://router.fabryka.ai/v1/chat/completions \
  -H "Authorization: Bearer $FABRYKA_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3.6-35b-a3b","messages":[{"role":"user","content":"Hello!"}]}'

Python (OpenAI SDK)

from openai import OpenAI
client = OpenAI(base_url="https://router.fabryka.ai/v1",
                api_key="sk-fab-...")
print(client.chat.completions.create(
    model="qwen3.6-35b-a3b",
    messages=[{"role": "user", "content": "Hello!"}],
).choices[0].message.content)

Other agents / OpenAI-SDK tools (env vars)

export OPENAI_BASE_URL="https://router.fabryka.ai/v1"
export OPENAI_API_KEY="sk-fab-..."   # model: qwen3.6-35b-a3b

Using Hermes? Env vars do not work for its main model — edit ~/.hermes/config.yaml: see /hermes →

Pricing: $0.20 / 1M input · $0.60 / 1M output. Rate-limited; single model; beta. Full guide: /docs →