BETA

Docs
Documentation

Create completion

POST/v1/completions

The legacy plain-text completion protocol (a prompt string in, generated text out) — for clients that haven't migrated to the chat format yet. Forwarded the same generic way as every other route.

Request body

model
required, string — a catalog id from GET /v1/models
prompt
required, string (or array of strings)
max_tokens
optional, number — capped server-side to what your balance can cover

cURL example

terminal
curl https://apily.pro/v1/completions \
  -H "Authorization: Bearer apily_your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.6-sol","prompt":"Once upon a time","max_tokens":50}'