> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openference.com/llms.txt
> Use this file to discover all available pages before exploring further.

# POST /v1/images/generations

> OpenAI-compatible image generation endpoint.

# POST /v1/images/generations

Generate an image from a text prompt using an image-capable model, with the standard OpenAI images request shape.

```bash theme={null}
curl https://api.openference.com/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sensenova-u1-fast",
    "prompt": "A minimal flat vector icon of a paper airplane, blue on white",
    "size": "2048x2048"
  }'
```

Response:

```json theme={null}
{
  "created": 1783970000,
  "model": "SenseNova U1 Fast",
  "data": [
    { "url": "https://api.openference.com/assets/gen/9b6d2c1e-....png" }
  ],
  "usage": { "input_tokens": 13, "output_tokens": 16384, "total_tokens": 16397 }
}
```

## Parameters

| Field             | Type    | Notes                                                                                                                                                                                                                                                                                                      |
| ----------------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `model`           | string  | An image-generation model (see `GET /v1/models` — image models advertise `architecture.output_modalities: ["image"]`).                                                                                                                                                                                     |
| `prompt`          | string  | Required. Text description of the image.                                                                                                                                                                                                                                                                   |
| `n`               | integer | Only `1` is supported.                                                                                                                                                                                                                                                                                     |
| `size`            | string  | Optional `WIDTHxHEIGHT`. Supported: `2048x2048`, `2752x1536`, `1536x2752`, `1664x2496`, `2496x1664`, `1760x2368`, `2368x1760`, `1824x2272`, `2272x1824`, `3072x1376`, `1344x3136`, `2560x720`, `3072x864`. Other values (e.g. `1024x1024`) are mapped to the supported size with the closest aspect ratio. |
| `response_format` | string  | `url` (default) or `b64_json`.                                                                                                                                                                                                                                                                             |

## Daily limit

Image generation is limited to **10 images per account per day** (resets at 00:00 UTC). Exceeding it returns HTTP 429 with code `image_daily_limit_exceeded` and a `Retry-After` header.

## Notes

* Generated image URLs are hosted by Openference and remain valid — you can hot-link or download them.
* Image models cannot be used on the chat, responses, or embeddings endpoints (you'll get HTTP 400 `model_not_supported_on_endpoint`), and chat models cannot be used here.
* Image requests consume your plan's request quota like any other API call.