Reference · Images

POST /v1/images/generations

An OpenAI-images-compatible endpoint for guarded image generation. Prompts pass content + NSFW moderation before they ever reach Flux.

Overview

Guarded image generation

POST /v1/images/generations is OpenAI-images-compatible and uses your API key (Bearer auth). Every prompt runs through content moderation and an NSFW guard (English + Bahasa Indonesia) before it reaches the image model, and spend is metered like any other usage.

This page is the terse request/response reference. For the full walkthrough — enhance, styles, the studio UI, and cost — see the Image generation guide.

Request

Request body

Send a JSON body with the prompt and generation options:

curl https://api.anoman.io/v1/images/generations \
  -H "Authorization: Bearer anm-sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-schnell",
    "prompt": "A ceramic coffee mug on a walnut desk, soft morning light",
    "n": 1,
    "enhance": true,
    "style": "product-photo",
    "response_format": "b64_json"
  }'

Field	Description
model	Model allowlist: `flux-schnell` (default, ~$0.003/image) and `flux-1.1-pro` (~$0.04/image). Any other value returns 400.
prompt	The text prompt. Required.
n	Number of images, 1–4. Defaults to 1.
enhance	When true, a cheap LLM art-director rewrites the prompt for quality and strips 'AI slop'. The guard re-runs on the enhanced prompt before the image model.
style	Optional preset that steers the look: `product-photo`, `editorial`, `flat-illustration`, `3d-render`, `cinematic`.
response_format	Pass `b64_json` to receive base64 images inline. Otherwise the response returns ephemeral provider URLs.

Limits & guards

What's enforced

Daily cap. 100 images per API key per day.
Timeout. 90 seconds per generation.
Content + NSFW guard. Runs on the prompt (and on the enhanced prompt when enhance is on). Blocked prompts never reach the model.
Unknown model. Any model outside the allowlist returns 400.

Response

Response body

Each item carries data[].b64_json (when response_format is b64_json) or data[].url (ephemeral). revised_prompt reflects the final prompt actually sent to the model, and _anoman.enhanced_prompt surfaces the art-director's rewritten prompt.

{
  "created": 1740086400,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUg...",
      "revised_prompt": "Studio product photograph of a matte ceramic coffee mug..."
    }
  ],
  "_anoman": {
    "enhanced": true,
    "enhanced_prompt": "Studio product photograph of a matte ceramic coffee mug on a walnut desk, soft directional morning light, shallow depth of field, 50mm"
  }
}

Design in the studio.

Prompt composer, styles, Fast/Quality, palettes — all guarded.

Open studio Image generation guide