Model info
- Provided by: system-one.dev
- 1 credit per question per 4KB
- Up to 32 questions · 64KB per request
- Inputs: text and JSON
- Pick one: up to 255 options; Score: 2–10 levels
- Released 2026-10-07
Uses
- Tool routing: Pick one candidate tool, or decide that none of them fit. See Agent tool routing.
- Model routing: First judge how hard the request is, then send it to a small or large model. See Model routing.
- First-pass evaluation: Use Score against a rubric instead of an LLM as judge. See Using Score instead of an LLM as judge.
- Completion checks: Use a yes/no probability to decide whether an agent is done. See When an agent should stop.
- Guardrails: Judge whether input or output breaks a rule, then allow, block, or hand off. See Agent guardrails.
- Try it: Tweet moderation demo, Phishing-email demo (sample data; sign in to try live).
Open GET /v1/models · Developer docs · Try live (sign in required)