Generation

Generate one image with GPT Image 2

Native image generation with exact per-image reservation before dispatch. The Stable generation price matrix is published in /api/public/catalog. Provider identity and provider asset URLs remain private. URL results use short-lived Infer-signed content URLs; b64_json bytes are returned once and are not retained. Infer performs no automatic paid generation retry. A post-dispatch transport ambiguity leaves the reservation locked rather than guessing about provider spend.

post/v1/images/generations

Request

  • Base URL: https://infer.flow7.org
  • URL: https://infer.flow7.org/v1/images/generations
  • Auth: HTTP bearer

Headers

Idempotency-Keystring

Stable retry key scoped to the organization. Strongly recommended for any paid generation submission. Ambiguous post-dispatch outcomes are never automatically retried.

Request body

modelstring required

gpt-image-2 or infer/gpt-image-2:stable. Native image generation is currently Stable-only.

promptstring required
n1
quality'medium' | 'high'
sizestring

Must match a currently priced GPT Image 2 size in /api/public/catalog.

response_format'url' | 'b64_json'
output_format'png'
streamfalse

Image SSE is not currently exposed by Infer.

idempotency_keystring

Response

Completed image generation

createdinteger required

Changes

No recorded changes to this operation across all 1 revision of this API.