OpenAI-compatible · qwen3.6-35b-a3b

Frontier reasoning,
one clean endpoint.

Sign up with an email and get $100 of free credit — no card, no waiting. Call a 35B reasoning model through the API you already know.

$0.20 / 1M input · $0.60 / 1M output · rate-limited beta. Have a key?

/v1

Drop-in compatible

Point any OpenAI SDK or tool at the base URL. Chat completions, streaming, usage — all standard.

128K

Reasoning model

qwen3.6-35b-a3b — a 35B MoE that thinks before it answers, with a 128K context window.

$

Transparent metering

Pay-per-token against your balance. Check it anytime at /account or /v1/credits.

Integrate in 30 seconds

base urlhttps://router.fabryka.ai/v1 modelqwen3.6-35b-a3b api keysk-fab-… (from signup)
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!"}]}'

Full guide at /docs · using Hermes? see /hermes (env vars don't work — it needs config.yaml).