Image Model Matrix
This page summarizes image models currently listed on the pricing page, their recommended endpoints, input formats and result handling. Check the console, pricing page and GET /v1/models for actual model availability, sizes, counts and prices.
Model summary tables
| Model family. | Representative Model | Recommended entrance | Usual Mode | Query Entry |
|---|---|---|---|---|
| GPT Image | gpt-image-2, gpt-image-2-pro, gpt-image-2-vip | /v1/images/generations, /v1/images/edits, /v1/images/generations/async, /v1/images/edits/async | Text-to-image and image editing | Synchronous results return directly; query asynchronous tasks at /v1/images/tasks/{task_id} |
| Seedream / Wan asynchronous picture | seedream-5.0, seedream-4.5, wan2.7-image-pro | /v1/images/generations/async | text-to-image, image-to-image | /v1/images/tasks/{task_id} |
| Gemini Nano | gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, nano-banana-2, nano-banana-pro | Synchronous /v1beta/models/{model}:generateContent; /v1/images/generations/async when asynchronous access is enabled | Gemini-format image generation and unified asynchronous tasks | Synchronous results return directly; query asynchronous tasks at /v1/images/tasks/{task_id} |
| Doubao Seedream | doubao-seedream-4-5-251128, doubao-seedream-5-0-260128 | /v1/images/generations | text-to-image, Creative | synchronous returns, no task queries |
| Grok Imagine | grok-imagine-image, grok-imagine-image-pro | /v1/images/generations | text-to-image, Creative | synchronous returns, no task queries |
| Ideogram images | ideogram-* | /ideogram/generate, /ideogram/remix, /ideogram/upscale, /ideogram/describe | Text-to-image, remix, upscale and image descriptions | Follow the actual response |
| Midjourney task | mj-* | /mj/submit/* | Imagine, mixed, described, action task | /mj/task/{id}/fetch or /mj/task/list-by-condition |
Photo Open Model
| Models | Capacity | Input | Output |
|---|---|---|---|
gpt-image-2 | Picture Generation | Prompt | Photo URL or image content, as per API Reference |
gpt-image-2-pro | High-quality photo generation and editing | Prompt, Photo Files | Photo URL or image content, as per API Reference |
gpt-image-2-vip | GPT Image Fast or High Priority Mode | Prompt | Photo URL or image content, as per API Reference |
doubao-seedream-4-5-251128 | Seedream Image Generation | Prompt | Photo URL or image content, as per API Reference |
doubao-seedream-5-0-260128 | Seedream Image Generation | Prompt | Photo URL or image content, as per API Reference |
seedream-5.0 | asynchronous Photo Generation and image-to-image | Prompt, Photo URL | Image task result URL |
seedream-4.5 | asynchronous Photo Generation and image-to-image | Prompt, Photo URL | Image task result URL |
wan2.7-image-pro | asynchronous Photo Generation and image-to-image | Prompt, Photo URL | Image task result URL |
gemini-3.1-flash-image-preview | Gemini Image Generation | Gemini contents[] | Gemini-compatible response |
gemini-3-pro-image-preview | Gemini image generation; unified asynchronous tasks when enabled | Gemini contents[], or prompt on /v1/images/generations/async | Gemini-compatible response or image-task result URL |
nano-banana-2 | Gemini Nano Image Generation | Gemini contents[] | Gemini-compatible response |
nano-banana-pro | Gemini Nano Image Generation | Gemini contents[] | Gemini-compatible response |
grok-imagine-image | Grok Imagine Image Generation | Prompt | Photo URL or image content, as per API Reference |
grok-imagine-image-pro | Grok Imagine Pro Image Generation | Prompt | Photo URL or image content, as per API Reference |
ideogram-* | Text-to-image, remix, upscale and image descriptions | Prompt and image URL | Image result or descriptive text, according to the response |
mj-* | Imagine, mixed, described, action task | Prompt, Photo URL, action parameters | task status, progress, results picture and button action |
Enter media assets Mode
| Input method | Suitable uses | Call the asset API first? |
|---|---|---|
| Prompt | text-to-image, poster, styled creative map. | No need. Pass it to prompt. |
| Multipart Photo File | Picture editing and photo variants. | Not required. Directly to /v1/images/edits or /v1/images/variations. |
| Clients' own public network URL | Ideogram, Midjourney or model supports URL input. | Not required. Ensure that URLs are stable and accessible. |
| MoonNexAI OSS Test URL | For local document association only, there is no guarantee of long-term preservation or continued availability. | Call /v1/assets/uploads and use mode=oss; for official business, switch to the customer-owned public network URL. |
Generate Mode Support
| Model family. | text-to-image | Picture Editor | Picture variant | Mixed Chart | Zoom in. | Picture Description | Asynchronous tasks |
|---|---|---|---|---|---|---|---|
| GPT Image | Support | Available when supported | Based on model description | Not applicable | Not applicable | Not applicable | Support |
| Seedream / Wan asynchronous picture | Support | image-to-image Available | Not applicable | Not applicable | Not applicable | Not applicable | Support |
| Gemini Nano | Support | Based on model description | Not applicable | Not applicable | Not applicable | Based on Gemini Capability | Support when asynchronous capability is in place |
| Doubao Seedream | Support | Based on model description | Not applicable | Not applicable | Not applicable | Not applicable | Not applicable |
| Grok Imagine | Support | Based on model description | Not applicable | Not applicable | Not applicable | Not applicable | Not applicable |
| Ideogram images | Supported | Available for remix | Not applicable | Supported | Supported | Supported | Follow the actual response |
| Midjourney task | Support | Action task available | Action task available | Support | Support | Support | Support |
Common field
| field | Purpose |
|---|---|
model | Photo model name, required for General Image API. |
prompt | Photo description, with recommendations for subject, scene, style, aspect ratio and use. |
image | Multipart photo file for photo editing and transformation. |
image_url | Photo URL, used for Ideogram, picture description or compatibility URL input. |
size | Output sizes, e.g. 1024x1024, the exact value is based on the range of model support. |
aspect_ratio | Picture aspect ratio, e.g. 1:1, 16:9, 9:16. |
n | Generates the quantity. |
response_format | returns the format, which is based on API Reference. |
task_id | Picture asynchronous tasks ID, for GET /v1/images/tasks/{task_id}. |
notifyHook | The address of callback upon completion of Midjourney task. |
customId | Midjourney action task uses buttons or action IDs. |
Entry Selection
| Requirements | Recommended Model Family | Recommended Pages | Common field |
|---|---|---|---|
| Generate pictures from text | GPT Image, Doubao Seedream, Grok Imagine | Picture Generation | model, prompt, size, n |
| Time-consuming pictures generation or editing | GPT Image, Seedream / Wan asynchronous pictures, Gemini image model with asynchronous capabilities | Picture Step Task | model, prompt, size, resolution, task_id |
Use seedream-5.0, seedream-4.5, wan2.7-image-pro | Seedream / Wan asynchronous picture | Seedream / Wan Step Picture Model | model, input.messages, parameters.size |
| Upload original maps and modify them by description | GPT Image | Picture Editor | image, model, prompt, size |
| Generate pictures in Gemini format | Gemini Nano | Gemini Nano Synchronize Call | contents[], parts[].text |
| Posters, packaging or text layout | Ideogram Image | Ideogram text-to-image | prompt, aspect_ratio |
| Based on the image to continue mixing or zooming in | Ideogram Image | Ideogram Image | image_url, prompt, aspect_ratio |
| Submit high-stylish asynchronous pictures task | Midjourney task | Midjourney Imagine | prompt, notifyHook, customId |
Agreement description
MoonNexAI /v1/images/* uses OpenAI Images-compatible endpoints for models such as gpt-image-*, doubao-seedream-* and grok-imagine-*. Synchronous calls wait for completion. Asynchronous calls return a task ID queried at /v1/images/tasks/{task_id}. seedream-5.0, seedream-4.5, wan2.7-image-pro and enabled gemini-3-pro-image-preview accounts can use the asynchronous endpoint. Synchronous Gemini-compatible requests use /v1beta/models/{model}:generateContent. Check the console, pricing page and GET /v1/models for editing, variations, sizes, resolutions and output formats. Asynchronous access is not guaranteed for every API key group.
/v1/chat/completions is used for chat completion and is not a recommended photo generation portal for gpt-image-*. If you need a picture, call the Images API by the recommended entry in the model matrix.
Relevant Pages
- Overview of the Image Series
- GPT Image Synchronize Call
- GPT Image Elap
- Picture Step Task
- Seedream / Wan Step Picture Model
- Gemini Nano Synchronize Call
- Gemini Nano is a step call
- Doubao Seedream
- Grok Imagine
- OpenAI compatible overview
- Ideogram Image
- Midjourney Task
- Uploading and Media Asset Overview
- API Reference