GPT Image 2 / 2.5 / 2.6 Image Generation API

¶ 1. Get API Key

Open the Mai application list, enter an available application, and copy the API Key.

Get Mai API Key

¶ 2. Send the First Request

curl https://api.ai.moses.day/openai/images/generations \
  -H "Authorization: Bearer 你的 API Key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "Minimal editorial product illustration: one plain white ceramic coffee mug centered on a solid cobalt blue tabletop, pale cream background, soft shadow, clean geometric shapes, no text, no logo, portrait composition",
    "size": "1024x1536"
  }'

The image in a successful response is located at data[].url. Below is the 1024×1536 result actually obtained through an Mai request on September 8, 2026 (task d56455e2-e7f7-4bcd-b935-475b0a1e0948, trace eb938601-8192-407f-b539-1e0554b697ec):

White coffee mug generated by GPT Image 2

¶ 3. Common Parameters

Field	Description
`model`	`gpt-image-2` (recommended by default), `gpt-image-2.5-flare` (faster), or `gpt-image-2.5-sunburst` (higher fidelity and control); all three can select their corresponding `:official` variants, and `gpt-image-2` also supports `:reverse`
`prompt`	Image description, up to 32,000 characters
`size`	`auto` or `WIDTHxHEIGHT`; width and height must be multiples of 16, the longer side must not exceed 3840, total pixels must be 655,360–8,294,400, and the aspect ratio must not exceed 3:1
`n`	1–10; only 1 is supported when `response_format=b64_json`
`quality`	GPT Image models support `auto`, `low`, `medium`, `high`; 2.5 / 2.6 Flare / Sunburst (including `:official`) additionally support `xhigh`, `max`. Official channels are billed by actual Token usage
`response_format`	`url` or `b64_json`
`callback_url`	Optional; sends the result to this address after a long task is completed

Common sizes:

Ratio	1K	2K	4K
1:1	`1024x1024`	`2048x2048`	`2880x2880`
4:3	`1536x1024`	`2048x1536`	`3264x2448`
3:4	`1024x1536`	`1536x2048`	`2448x3264`
16:9	`1792x1024`	`2048x1152`	`3840x2160`
9:16	`1024x1792`	`1152x2048`	`2160x3840`

size: "auto" selects the canvas based on the ratio, pixels, and layout intent in the prompt; directly enter the dimensions when precise pixels are needed.

¶ Models and Billing Methods

Model	Applicable Scenarios and Billing Methods
`gpt-image-2`	Default reverse channel, fixed billing by number of successful images
`gpt-image-2:reverse`	Explicitly selects the reverse channel, fixed billing by number of successful images
`gpt-image-2:official`	Official API channel, higher stability, billed by actual Token usage
`gpt-image-2.5-flare`	Focuses on generation speed, fixed billing by number of successful images
`gpt-image-2.6-flare`	Focuses on generation speed, fixed billing by number of successful images
`gpt-image-2.5-flare:reverse`	Explicit reverse alias, equivalent to `gpt-image-2.5-flare`, fixed billing by number of successful images
`gpt-image-2.6-flare:reverse`	Explicit reverse alias, equivalent to `gpt-image-2.6-flare`, fixed billing by number of successful images
`gpt-image-2.5-flare:official`	Official API channel, higher stability and focused on generation speed, billed by actual Token usage
`gpt-image-2.6-flare:official`	Official API channel, higher stability and focused on generation speed, billed by actual Token usage
`gpt-image-2.5-sunburst`	Focuses on high fidelity and fine control, fixed billing by number of successful images
`gpt-image-2.6-sunburst`	Focuses on high fidelity and fine control, fixed billing by number of successful images
`gpt-image-2.5-sunburst:reverse`	Explicit reverse alias, equivalent to `gpt-image-2.5-sunburst`, fixed billing by number of successful images
`gpt-image-2.6-sunburst:reverse`	Explicit reverse alias, equivalent to `gpt-image-2.6-sunburst`, fixed billing by number of successful images
`gpt-image-2.5-sunburst:official`	Official API channel, higher stability and focused on high fidelity and fine control, billed by actual Token usage
`gpt-image-2.6-sunburst:official`	Official API channel, higher stability and focused on high fidelity and fine control, billed by actual Token usage

2.0 / 2.5 reverse models (including :reverse aliases) may use GPT Image 2.5 Flare to complete requests during automatic recovery; the requested model and the billing method based on the number of successful images remain unchanged.

The displayed price for the official API channel is an estimate before the request; the final amount is subject to the actual Token usage and usage records in the response.

¶ 4. Multiple Image Generation

curl https://api.ai.moses.day/openai/images/generations \
  -H "Authorization: Bearer 你的 API Key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A small fox reading under a glowing mushroom, watercolor illustration",
    "size": "1536x1024",
    "n": 2
  }'

gpt-image-2, gpt-image-2.5-flare, gpt-image-2.5-sunburst, and their :reverse aliases are billed by the number of successfully generated images; gpt-image-2:official, gpt-image-2.5-flare:official, and gpt-image-2.5-sunburst:official are billed based on the actual Tokens for text input and image output in the response. The page price is an estimate before the request; the final amount is based on usage records.

¶ 5. Asynchronous Callbacks

After adding callback_url to the request body, the API will first return {"task_id": "..."}, and POST the final result to that URL upon completion; synchronous requests will still return created and data:

{
  "model": "gpt-image-2",
  "prompt": "A product poster with clear typography",
  "size": "1024x1024",
  "callback_url": "https://example.com/webhooks/images"
}

The callback receiver should use task_id for deduplication, and verify the request source and data format.

¶ 6. Troubleshooting

Status	Check
400	Combination of `model`, `prompt`, size format, `n`, and `response_format`
401	Whether the API Key is complete, and whether the Header is `Authorization: Bearer ...`
429	Requests are too frequent; retry later
504	Synchronous generation timed out; use `callback_url` instead

Error responses will include error.code, error.message, and trace_id. When reporting an issue, provide the trace_id; do not provide the API Key.

For complete fields and real-time enumerations, refer to the OpenAI Images Generations API page. For image editing, see GPT Image 2 / 2.5 / 2.6 Image Editing.

¶ GPT Image 2.6

GPT Image 2.6 continues to use the generation, editing, asynchronous task, and billing APIs from 2.5:

Model	Billing
`gpt-image-2.6-flare` / `gpt-image-2.6-flare:reverse`	0.22 Credits/image
`gpt-image-2.6-sunburst` / `gpt-image-2.6-sunburst:reverse`	0.22 Credits/image
`gpt-image-2.6-flare:official`	Same as 2.5 official, billed by actual Token usage
`gpt-image-2.6-sunburst:official`	Same as 2.5 official, billed by actual Token usage

Available quality options are auto, low, medium, high, xhigh, and max; use auto for size or a WIDTHxHEIGHT that meets the above constraints. This API supports png, jpeg, and webp, and does not currently support SVG/GIF. Editing supports JSON image URLs and multipart file uploads. :reverse is an explicit alias for the standard version with the same name. Please use the full model name; do not pass gpt-image-2.6.