All models · Pricing · API docs
clef-flash API
Cloudflare/clef-flash (Qwen3.5-9B with a decision head, Apache-2.0) on our own GPUs in Russia · the same /v1/decisions as frida-decisions with model=clef-flash: long text up to 8k tokens, stronger on English and fine distinctions. Types choice, score, noul (no ranking) · ~150 ms · a unit counts ×4 · /v1/decisions
- Type: text decisions · решения по тексту · выбор варианта, шкала, да/нет · длинный контекст
- Context: 8192
- Access: all plans
- Endpoint: /v1/decisions
Runs on our own GPUs in Russia.
How to connect: change one line — base_url. Get an sk- key in the dashboard.
curl https://api.neuraldeep.ru/v1/decisions \
-H "Authorization: Bearer $NEURALDEEP_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"clef-flash","state":"My verification code never arrives","questions":{"topic":{"type":"choice","instructions":"Which topic?","criteria":{"login":"sign-in, codes","payment":"payments, refunds"}}}}'