Models
Every model id of the Cheapest Imagen API with the official OpenAI or Google model it runs, the resolutions it makes and its credits per image.
Pass one of these ids in the model field. Each id runs one official model from OpenAI or Google; where an id is a particular channel of that model, the table says so.
| API id | Official model | Resolutions | Credits per image |
|---|---|---|---|
gpt-image-2 | OpenAI gpt-image-2 | 1K | 8 |
gpt-image-2-adobe | OpenAI gpt-image-2, through Adobe’s channel | 1K, 2K, 4K | 20 |
gpt-image-2.5 | OpenAI GPT Image 2.5 | 1K | 8 |
gpt-image-2.5-flare | OpenAI gpt-image-2.5-flare, the fast version | 1K, 2K, 4K | 20 |
gpt-image-2.5-sunburst | OpenAI gpt-image-2.5-sunburst, the detail version | 1K, 2K, 4K | 25 |
gpt-image-2.6 | OpenAI GPT Image 2.6 | 1K | 8 |
gpt-image-2.6-flare | OpenAI gpt-image-2.6-flare, the fast version | 1K, 2K, 4K | 20 |
gpt-image-2.6-sunburst | OpenAI gpt-image-2.6-sunburst, the detail version | 1K, 2K, 4K | 25 |
nano-banana-2 | Google gemini-3.1-flash-image-preview | 1K, 2K, 4K | 12 |
nano-banana-2.1 | Google gemini-nano-banana-2.1 | 1K, 2K, 4K | 12 |
nano-banana-pro | Google gemini-3-pro-image-preview | 1K, 2K, 4K | 20 |
nano-banana-2-1k | Google gemini-3.1-flash-image-preview, stable channel | 1K | 60 |
nano-banana-2-2k | Google gemini-3.1-flash-image-preview, stable channel | 2K | 90 |
nano-banana-2-4k | Google gemini-3.1-flash-image-preview, stable channel | 4K | 130 |
nano-banana-pro-1k | Google gemini-3-pro-image-preview, stable channel | 1K | 100 |
nano-banana-pro-2k | Google gemini-3-pro-image-preview, stable channel | 1K, 2K | 100 |
nano-banana-pro-4k | Google gemini-3-pro-image-preview, stable channel | 4K | 180 |
How to read the ids
gpt-image-2,gpt-image-2.5,gpt-image-2.6are the GPT Image generations at 1K; the model picks the quality.gpt-image-2-adobeis OpenAI’s gpt-image-2 reached through Adobe’s channel. It adds 2K and 4K, quality levels and custom sizes. Its images carry Adobe’s content credentials.-flareand-sunburstare OpenAI’s own two versions of GPT Image 2.5 and 2.6: Flare for speed, Sunburst for detail and consistent edits.nano-banana-2,nano-banana-2.1,nano-banana-proare Google’s Gemini image models, under the names people know them by.- Ids ending in
-1k,-2k,-4kare the same Google model on a dearer, steadier channel, fixed to that resolution (nano-banana-pro-2kmakes 1K and 2K). On these an image refused for its content is still charged.
GET /v1/models returns the same list for your key, with official_model, resolutions and credits_per_image for each id.
Quality levels, output formats and sizes of each model are in Text to image and Ratios and sizes.
Text to image
Generate images from a text prompt with the Cheapest Imagen API, and choose the model, size, quality, number of images and output file format.
Edit images
Image to image with the Cheapest Imagen API. Send one or more reference images to /v1/images/edits with GPT Image or Nano Banana, as files or as links, and describe the change.