Skip to content

Overview of the Image Series ​

Image series are model names by price pages and model lists that customers see. Common current image models include gpt-image-2, gpt-image-2-pro, gpt-image-2-vip, doubao-seedream-4-5-251128, doubao-seedream-5-0-260128, seedream-5.0, seedream-4.5, wan2.7-image-pro, gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, nano-banana-2, nano-banana-pro, grok-imagine-image and grok-imagine-image-pro. Different models use the Unified Photo Entry, the Gemini-compatible entrance or the task entry.

Route List ​

MethodologyPathPurpose
POST/v1/images/generationsPicture generation.
POST/v1/images/generations/asyncPicture asynchronous generated.
POST/v1/images/editsPicture editing.
POST/v1/images/edits/asyncPhoto asynchronous Edit.
GET/v1/images/tasks/{task_id}Find pictures asynchronous tasks.
GET/v1/images/tasks/{task_id}/contentGet a picture of the result of asynchronous tasks.
POST/v1/images/variationsPicture variant.
POST/ideogram/generateIdeogram text-to-image.
POST/ideogram/remixIdeogram mixed.
POST/ideogram/upscaleIdeogram zoom in.
POST/ideogram/describePicture description.
POST/mj/submit/imagineMidjourney Imagine task.
POST/mj/submit/blendMidjourney mixed task.
POST/mj/submit/describeMidjourney describes task.
GET/mj/task/{id}/fetchQuery Midjourney single task.
POST/mj/task/list-by-conditionBatch query Midjourney task.

Basic processes ​

  1. View Image Model Matrix, confirm the model family, how it is entered and how it returns.
  2. For gpt-image-*, doubao-seedream-* and grok-imagine-*, start with the OpenAI Images overview.
  3. If you need a stable re-use for the photo input, read Uploading and Media Asset Overview first.
  4. Call the endpoint and save model, request parameters and image URLs. For long tasks, use asynchronous image tasks.
  5. Midjourney task needs to save task ID and obtain results from Midjourney Task Query or callback.

Model Directory ​

ContentsFit to scene
GPT Image Synchronize Callgpt-image-2, gpt-image-2-pro, gpt-image-2-vip synchronous generation and editing.
GPT Image ElapGPT Image asynchronous Generation, asynchronous Editor and task query.
Gemini Nano Synchronize Callgemini-*-image-preview and nano-banana-* generate pictures in Gemini-compatible format.
Gemini Nano asynchronous requestsEnabled Gemini image models use the unified image-task API.
Doubao SeedreamText-to-image and image creation with doubao-seedream-*.
Seedream / Wan asynchronous imagesAsynchronous text-to-image and image-to-image with seedream-5.0, seedream-4.5 and wan2.7-image-pro.
Grok Imaginegrok-imagine-image and grok-imagine-image-pro images generated.
Ideogram ImagePosters, packaging, text layout, mixed maps, magnification and photo descriptions.
Midjourney TaskImagine, mixed, variant, magnification, description and action task.

Standard request ​

bash
curl https://moonnexai.com/v1/images/generations \
  -H "Authorization: Bearer <MOONNEXAI_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A clean product mockup on a white studio table.",
    "size": "1024x1024",
    "n": 1
  }'

Recommended order of reading ​

  1. Image Model Matrix
  2. OpenAI compatible overview
  3. Picture Step Task
  4. Midjourney Task Query
  5. Picture Generation Guide
  6. Overview of mandate management