GPT Image 2.5

OpenAI · ~1.5 min

from $0.010per picture

The ChatGPT image model: realistic photos, neat lettering, product shots and precise photo edits.

Edit a photo gpt-image-2.5-image-to-image · $0.010–$0.710 (depends on quality and resolution)Create a picture gpt-image-2.5-text-to-image · $0.010–$0.710 (depends on quality and resolution)

Mode	ID	Price
Edit a photo	`gpt-image-2.5-image-to-image`	$0.010–$0.710 (depends on quality and resolution)
Create a picture	`gpt-image-2.5-text-to-image`	$0.010–$0.710 (depends on quality and resolution)

Edit a photo Create a picture

Edit a photo

Upload a photo and describe what to change. ID: gpt-image-2.5-image-to-image · $0.010–$0.710 (depends on quality and resolution) per image · ~1.5 min

Parameters (field input)

Parameter	Required	Description	Values (default in bold)
`prompt`	yes	What to draw or what to change	text, up to 20000 chars
`input_urls`	yes	Links to your photos (https), up to 16	`["https://…"]`
`resolution`	no	Long side: 0.5K ≈ 512 px, 1K ≈ 1024 px, 2K ≈ 2048 px, 4K ≈ 4096 px. Sizes above native are an upscale of the finished picture (Lanczos + light sharpening): 4K on Nano Banana 2 and Pro from 2K, 2K on Nano Banana from 1K, 2K and 4K on GPT Image from its native ~1.5K	`1K` `2K` `4K`
`aspect_ratio`	no	Image shape	`auto` `1:1` `1:3` `3:1` `3:2` `2:3` `4:3` `3:4` `5:4` `4:5` `16:9` `9:16` `2:1` `1:2` `21:9` `9:21`
`output_format`	no	File format	`png` `jpeg` `webp`
`background`	no	Background: `auto`, `opaque`, `transparent` (only with `png` or `webp`)	`auto` `opaque` `transparent`
`moderation`	no	Accepted for apimart compatibility, does not change the result	`low` `auto`
`quality`	no	Rendering effort; passed to ChatGPT. Changes the price (see the table below), `auto` = `medium`	`auto` `low` `medium` `high` `xhigh` `max`

Example

curl -X POST https://mixmedia.tech/api/v1/jobs/createTask \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-image-2.5-image-to-image","input":{"prompt":"Make the background a neon city at night","input_urls":["https://mixmedia.tech/static/img/previews/gpt-t2i.jpg"],"resolution":"1K","aspect_ratio":"auto","moderation":"low","quality":"auto"}}'

import os, requests

r = requests.post(
    "https://mixmedia.tech/api/v1/jobs/createTask",
    headers={"Authorization": f"Bearer {os.environ['API_KEY']}"},
    json={
      "model": "gpt-image-2.5-image-to-image",
      "input": {
        "prompt": "Make the background a neon city at night",
        "input_urls": [
          "https://mixmedia.tech/static/img/previews/gpt-t2i.jpg"
        ],
        "resolution": "1K",
        "aspect_ratio": "auto",
        "moderation": "low",
        "quality": "auto"
      }
    },
)
print(r.json())  # {"code": 200, "data": {"taskId": "..."}}

const r = await fetch("https://mixmedia.tech/api/v1/jobs/createTask", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.API_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({
    "model": "gpt-image-2.5-image-to-image",
    "input": {
      "prompt": "Make the background a neon city at night",
      "input_urls": [
        "https://mixmedia.tech/static/img/previews/gpt-t2i.jpg"
      ],
      "resolution": "1K",
      "aspect_ratio": "auto",
      "moderation": "low",
      "quality": "auto"
    }
  }),
});
console.log(await r.json()); // { code: 200, data: { taskId: "..." } }

Create a picture

Describe the picture and the model creates it from scratch. ID: gpt-image-2.5-text-to-image · $0.010–$0.710 (depends on quality and resolution) per image · ~1.5 min

Parameters (field input)

Parameter	Required	Description	Values (default in bold)
`prompt`	yes	What to draw or what to change	text, up to 20000 chars
`resolution`	no	Long side: 0.5K ≈ 512 px, 1K ≈ 1024 px, 2K ≈ 2048 px, 4K ≈ 4096 px. Sizes above native are an upscale of the finished picture (Lanczos + light sharpening): 4K on Nano Banana 2 and Pro from 2K, 2K on Nano Banana from 1K, 2K and 4K on GPT Image from its native ~1.5K	`1K` `2K` `4K`
`aspect_ratio`	no	Image shape	`auto` `1:1` `1:3` `3:1` `3:2` `2:3` `4:3` `3:4` `5:4` `4:5` `16:9` `9:16` `2:1` `1:2` `21:9` `9:21`
`output_format`	no	File format	`png` `jpeg` `webp`
`background`	no	Background: `auto`, `opaque`, `transparent` (only with `png` or `webp`)	`auto` `opaque` `transparent`
`moderation`	no	Accepted for apimart compatibility, does not change the result	`low` `auto`
`quality`	no	Rendering effort; passed to ChatGPT. Changes the price (see the table below), `auto` = `medium`	`auto` `low` `medium` `high` `xhigh` `max`

Example

curl -X POST https://mixmedia.tech/api/v1/jobs/createTask \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-image-2.5-text-to-image","input":{"prompt":"A cat astronaut in a neon city, cinematic light","resolution":"1K","aspect_ratio":"auto","moderation":"low","quality":"auto"}}'

import os, requests

r = requests.post(
    "https://mixmedia.tech/api/v1/jobs/createTask",
    headers={"Authorization": f"Bearer {os.environ['API_KEY']}"},
    json={
      "model": "gpt-image-2.5-text-to-image",
      "input": {
        "prompt": "A cat astronaut in a neon city, cinematic light",
        "resolution": "1K",
        "aspect_ratio": "auto",
        "moderation": "low",
        "quality": "auto"
      }
    },
)
print(r.json())  # {"code": 200, "data": {"taskId": "..."}}

const r = await fetch("https://mixmedia.tech/api/v1/jobs/createTask", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.API_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({
    "model": "gpt-image-2.5-text-to-image",
    "input": {
      "prompt": "A cat astronaut in a neon city, cinematic light",
      "resolution": "1K",
      "aspect_ratio": "auto",
      "moderation": "low",
      "quality": "auto"
    }
  }),
});
console.log(await r.json()); // { code: 200, data: { taskId: "..." } }

Price by quality and resolution

Per picture. auto costs the same as medium.

`quality`	1K	2K	4K
`auto`	$0.010	$0.030	$0.040
`low`	$0.010	$0.010	$0.020
`medium`	$0.010	$0.030	$0.040
`high`	$0.050	$0.110	$0.180
`xhigh`	$0.090	$0.190	$0.320
`max`	$0.210	$0.430	$0.710

Compatibility

apimart/OpenAI-style requests work too:

model: gpt-image-2.5-image-to-image, gpt-image-2-image-to-image, gpt-image-2.5-text-to-image, gpt-image-2-text-to-image, gpt-image-2.5, gpt-image-2-5, gpt-image-2.5-flare, gpt-image-2.5-sunburst.
size instead of aspect_ratio: a ratio (16:9) or exact pixels (1600x1200) — we use the closest supported ratio.
Photos can go in image_urls, image_input or input_urls. Parameters may also be sent at the top level of the body, without the input wrapper.
resolution in any case (1k, 2K); jpg and jpeg are the same. n must be 1 (one image per request).
One name, gpt-image-2.5, for both modes: with photos the task runs as Photo → Photo. resolution: 1k, 2k or 4k — ChatGPT draws about 1.5K; 2K and 4K are an upscale of the finished picture (Lanczos + light sharpening) to a 2048 / 4096 px long side. quality (auto, low, medium, high, xhigh, max; hd = high, standard = medium) is passed to ChatGPT: the size stays the same, detail changes a little; the price follows the table below. model: gpt-image-2.5-flare and gpt-image-2.5-sunburst are the same model. moderation and mask_url are accepted but do not change the result.

Result

Same as any task: call recordInfo or receive a callback. Image links are in resultJson (kept for 24 hours).

Upload your photos via files/upload or pass any public https links.

#Edit a photo

#Create a picture

#Price by quality and resolution

#Compatibility

#Result

Edit a photo

Create a picture

Price by quality and resolution

Compatibility

Result