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

# Image API Overview

> Choose a supported image model family and its generation or editing request format.

Choose an image family before building the request. Use the request format and model-specific fields documented on its interface page.

## Image APIs

| Family | Generation | Editing | Request Format |
| - | - | - | - |
| GPT Image | [GPT Image](/api-reference/endpoint/gpt-image) | [Image edits](/api-reference/endpoint/gpt-image-edit) | Generation: JSON. Editing: multipart/form-data. |
| Grok Imagine | [Grok Imagine](/api-reference/endpoint/grok-imagine-image) | [Image edits](/api-reference/endpoint/grok-imagine-edit) | JSON for generation and editing; image references use native objects. |
| Qwen Image | [Qwen Image](/api-reference/endpoint/qwen-image) | [Image edits](/api-reference/endpoint/qwen-image-edit) | Basic generation: `input.prompt`; multimodal generation/editing: `input.messages`. Both use `model` and `parameters`. |
| Gemini | [Gemini](/api-reference/endpoint/nano-banana) | [Native image edits](/api-reference/endpoint/nano-banana) | `contents`, `generationConfig` |

[Gemini streaming requests](/api-reference/endpoint/nano-banana-stream)

## Available Model IDs

| Family | Model IDs |
| - | - |
| GPT Image | `gpt-image-2.5-sunburst`, `gpt-image-2.5-flare`, `gpt-image-2`, `gpt-image-1.5`, `gpt-image-1` |
| Grok Imagine | `grok-imagine-image-2.0`, `grok-imagine-image-quality`, `grok-imagine-image` |
| Qwen Image | `qwen-image-2.0-pro`, `qwen-image-2.0`, `qwen-image-max`, `qwen-image-plus`, `qwen-image`, `qwen-image-edit-max`, `qwen-image-edit-plus`, `qwen-image-edit` |
| Gemini | `gemini-nano-banana-2.1`, `gemini-3.1-flash-image`, `gemini-3.1-flash-image-preview`, `gemini-3-pro-image`, `gemini-3-pro-image-preview`, `gemini-3.1-flash-lite-image`, `gemini-2.5-flash-image` |

Account-visible models are returned by [`GET /v1/models`](/api-reference/endpoint/list-models). A model that accepts images as input is not necessarily an image-generation model. Use the family page to choose the output-capable model and the correct request format.

## Authentication

```bash theme={null}
curl "https://api.mixroute.ai/v1/models" \
  --header "Authorization: Bearer $MIXROUTE_API_KEY"
```

Use the exact model ID returned for your account. Availability and billing depend on the selected route; consult the Model Marketplace for account-specific information. Do not reuse another family's size, quality, input-image, or response-format fields.


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