Paste the JSON an LLM actually returned and the JSON Schema you expected it to follow — see exactly which fields are missing, wrong-typed, or out of range. Supports a documented subset of JSON Schema (same as the JSON Schema → AI Prompt tool) — not full spec compliance, but enough to catch the mistakes models actually make. Runs entirely in your browser.
curl -sS -X POST https://devops.majbase.com/json-schema-validator/api -H "Content-Type: application/json" -d '{"instance":{"name":"Ivan","age":-5},"schema":{"type":"object","properties":{"name":{"type":"string"},"age":{"type":"integer","minimum":0}},"required":["name","age"]}}'Returns {"valid": bool, "errors": [{"path", "message"}, ...]}, or {"error": "..."}.