One request. Typed answers.

Endpoint

POST https://ai-jev.pro/api/v1/systemone

Authenticate with Authorization: Bearer YOUR_JEV_API_KEY. Create or rotate keys in Account → API keys.

Request shape

Provide a model ID, the text or JSON to evaluate, and a map of named questions. Question types are noul (yes/no), choice, or score. A request can include up to 8 questions and 32 KiB of combined text and question definitions.

curl https://ai-jev.pro/api/v1/systemone \
  -H "Authorization: Bearer $JEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"state":"...", "questions":{"is_relevant":{"type":"noul","instructions":"Is this relevant?"}}}'

Response and billing

Answers include their chosen value and provider confidence/probabilities. Jev bills model input tokens at the displayed model rate; output tokens are not charged. Failed provider requests are reversed.

Responses include X-Jev-Credits-Charged, X-Jev-Input-Tokens, and X-Jev-Tokens-Remaining headers.

Images

Vision models accept up to four PNG, JPEG, or WebP images (4 MiB each, 8 MiB total). Images remain in the request and are not added to saved configuration history.