Documentation

Create image

POST/v1/images/generations

Image-generation models are proxied the same generic way as chat models — no separate onboarding, just a different catalog id.

Start

Help

Python Setup

Node.js Setup

PHP Setup

API Reference

cURL example

terminal

curl https://apily.pro/v1/images/generations \
  -H "Authorization: Bearer apily_your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"<image-model-id>","prompt":"a cyberpunk city skyline","n":1,"size":"1024x1024"}'

Response

Mirrors the upstream provider's response — an array of generated images, each as a url or b64_json depending on the model.

Error responses

Symptom	Cause	Fix
`400 Invalid value for n`	`n` is not a whole number from 1 to 10.	Send `n` between 1 and 10, or omit it (defaults to 1).
`401 Missing API key`	No auth header was sent.	Apily accepts `Authorization: Bearer …` and `x-api-key: …`.
`401 Invalid API key`	Key copied with stray spaces, truncated, or revoked.	Copy the key whole from the API page in your Apily account, the `apily_` prefix included.
`403 Email not verified`	Your Apily account's email address isn't verified yet.	Verify your email from the banner in the Apily app, then retry.
`404 Model not found`	The model ID isn't in the Apily catalog.	Copy the exact ID from `GET /v1/models` or the Models page in your account.
`503 Model temporarily unavailable`	The model exists, but no upstream provider is reachable right now.	Retry in a moment — it usually recovers within a minute. Switch models if it keeps happening.
`402 Insufficient balance`	Your token balance can't cover the request's estimated cost.	Top up your balance on the Billing page in your Apily account.
`429 Too many requests`	Your account sent more than 600 `/v1/*` requests in a minute — all of your API keys share one budget. The body is `{ error: { message, type: "rate_limit_error", code: "rate_limit_exceeded" }, retryAfterSeconds }`.	Wait the `Retry-After` header (or `retryAfterSeconds`) before retrying, and lower request concurrency.
`502 Upstream error`	The upstream provider returned an unexpected error.	Retry the request; try a different model if it persists.

Image models are billed per image. Per-image models charge the model price × the number of images returned (n, 1–10). Token-priced models charge the prompt text, each input image and the generated image(s) by the real usage the provider returns. Before the call a conservative upper bound is reserved (up to 10,000 output tokens per requested image), so a request can get 402 even when the final cost would fit your balance; the unused part of the reserve is returned right after the response.