Generate images (OpenAI-compatible)

Server URLloading...

POST

/v1/images/generations

Send

Authorization

Body

The billing unit depends on the model — the catalogue shows whether it prices per image or per token. Requesting several images bills each image separately either way. A request can also be served by a backup model if the primary upstream is down; the response headers name the model that actually answered.

Per-model limits (openai/gpt-image-2.5-sunburst, openai/gpt-image-2.5-flare, openai/gpt-image-2):

• Standard size: auto (default), 1024x1024, 1536x1024, 1024x1536. Output is about 1.5 MP; size only sets the aspect ratio and quality does not change the output or the price. Other sizes return 400.
• n: up to 4 for openai/gpt-image-2; 1 for flare and sunburst.
• The response is always {created, data:[{b64_json}]} (base64 PNG); response_format has no effect.
• openai/gpt-image-2.5-sunburst 2K / 4K: 2048x2048, 2560x1440, 1440x2560 or "2K" = 2K at $0.08 per image; 3840x2160, 2160x3840 or "4K" = 4K at $0.12 per image (standard is $0.0186). 2K / 4K requires n = 1, ignores quality, does not support mask, and is never retried or served by a backup model. Unlisted sizes return 400 and are not charged.

xai/grok-imagine-image-2.0: quality is low (default; auto means low) or medium; resolution is 1k (default), 1.5k or 2k; aspect_ratio sets the frame; n up to 4. Priced per image by quality × resolution, see the model page. Other quality or resolution values return 400 and are not charged.

See Images: Parameters vs. OpenAI for the full list of supported and unsupported parameters.

Response Body

curl -X POST "https://example.com/v1/images/generations" \  -H "Content-Type: application/json" \  -d '{    "model": "xai/grok-imagine-image-2.0",    "prompt": "A watercolor lighthouse on a cliff",    "quality": "medium",    "resolution": "2k",    "aspect_ratio": "16:9"  }'

{  "model": "string",  "stream": true}