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

# Images

> Painting / image generation APIs on Omniall AI.

# Images

Omniall AI exposes painting models mainly through:

| Style | Path | Typical models |
| - | - | - |
| OpenAI Images (recommended) | `POST /v1/images/generations` / `edits` | GPT-Image, Flux, Grok Imagine, Seedream, many Gemini image models, DALL·E |
| Gemini Chat | `POST /v1/chat/completions` | `gemini-nano-banana-2.1`, Flash/Pro image models (`image_url` / PDF `file` / `video_url`) |
| Gemini native | `POST /v1beta/models/{model}:generateContent` | Same models with `responseModalities: ["TEXT","IMAGE"]` |
| Midjourney proxy | `/mj/submit/*` + `GET /mj/task/{id}/fetch` | Midjourney via MJ proxy |

**API host:** `https://api.omniall.ai` · pick `model` from the [Model Square](https://omniall.ai/pricing).

**Banana 2.1** (`gemini-nano-banana-2.1`) supports image, **PDF**, and **short video** references. See [Gemini native format](/api-reference/endpoints/gemini-native-image) and [Chat image generation](/api-reference/endpoints/gemini-chat-image).

Browse the nested groups below: **General**, **Gemini**, **Jimeng / Seedream**, **GPT-Image**, **Midjourney**, **Flux**, **Grok**.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.