# GPT Image 2

ID: openai/gpt-image-2
Type: image generation
Vendor: OpenAI
Released: 2026-04-21
Description: OpenAI’s GPT Image 2 model for fast, high-quality text-to-image generation and reference-image editing with flexible sizes.

## Modes and inputs
- Text → Image (`txt->img`)
  - Prompt only, no input images
- Image → Image (`img->img`)
  - any image: up to 16

## Output
- Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 5:4. Other ratios snap to the closest one. Without `size` (or with `"auto"`), Mynth picks a ratio for the prompt.
- 4K: no
- Negative prompt: not supported (dropped, no error)

## Pricing (USD)
- Per image: $0.12
- Per input image: $0.020, charged once for each image it goes into
- Only successful results are charged.

## Usage
Set the request's `model` field to `openai/gpt-image-2`. Always pass it explicitly.

TypeScript SDK, Text → Image:

```ts
import Mynth from "@mynthio/sdk";

const mynth = new Mynth();

const task = await mynth.image.generate({
  model: "openai/gpt-image-2",
  prompt: "A lighthouse at dusk, 35mm film",
  size: "16:9",
});

console.log(task.urls[0]);
```

REST (cURL), Text → Image:

```bash
curl https://api.mynth.io/image/generate \
  -H "Authorization: Bearer $MYNTH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-image-2",
    "prompt": "A lighthouse at dusk, 35mm film",
    "size": "16:9"
  }'
```

CLI, Text → Image:

```bash
npx @mynthio/cli image generate \
  -m openai/gpt-image-2 \
  -p "A lighthouse at dusk, 35mm film" \
  -s 16:9
```

TypeScript SDK, Image → Image:

```ts
import Mynth from "@mynthio/sdk";

const mynth = new Mynth();

const task = await mynth.image.generate({
  model: "openai/gpt-image-2",
  prompt: "The same lighthouse, now in heavy fog",
  inputs: ["https://cdn.example.com/lighthouse.png"],
});

console.log(task.urls[0]);
```

REST (cURL), Image → Image:

```bash
curl https://api.mynth.io/image/generate \
  -H "Authorization: Bearer $MYNTH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-image-2",
    "prompt": "The same lighthouse, now in heavy fog",
    "inputs": ["https://cdn.example.com/lighthouse.png"]
  }'
```

CLI, Image → Image:

```bash
npx @mynthio/cli image generate \
  -m openai/gpt-image-2 \
  -p "The same lighthouse, now in heavy fog" \
  -i https://cdn.example.com/lighthouse.png
```

## Working with GPT Image 2

GPT Image 2 is OpenAI's image model for production work: layouts with dense,
readable text, edits that stay faithful to the source, and scenes that draw on
what the model knows about the world rather than on a reference image. OpenAI
released it on 21 April 2026, as the snapshot `gpt-image-2-2026-04-21`.

### What it is good at

- **Typography.** Posters, packaging, menus and UI mockups with text that reads,
  including long lines and small sizes.
- **Multilingual text.** Text rendered in scripts other than Latin.
- **Edits with references.** Up to 16 input images per request, in any role.
  Describe what should change and what must stay.
- **World knowledge.** Recognisable places, objects and styles from the prompt
  alone, without an image to copy from.
- **Flexible framing.** Eight aspect ratios from 9:16 to 16:9, each at a native
  resolution around 2K.

### Prompting

Write the prompt the way you would brief a designer: the subject, the setting,
the composition, then the finish.

- Put any text that must appear in quotes, and say where it goes:
  `a poster with the headline "Night Market" across the top`.
- Name the medium and the light: `35mm film, overcast daylight`, or
  `studio product shot, soft box from the left`.
- For an edit, say what stays the same before what changes:
  `keep the model and the jacket; replace the street with a beach at dusk`.
- Ask for one image and refine the prompt before raising `count`. Every image
  is charged, and a better prompt costs nothing.

### Rights

OpenAI assigns the rights in outputs to you, and commercial use is allowed.
Attribution is optional. OpenAI does not train on data sent through its
business API unless you opt in.

## Links
- Model page: https://mynth.io/models/openai%2Fgpt-image-2
- Playground: https://mynth.io/playground?_m=openai%2Fgpt-image-2
- Vendor page: https://platform.openai.com/docs/models/gpt-image-2
- API docs (image generation request): https://mynth.io/docs/api-reference/endpoints/image/generate.md
- Quickstart: https://mynth.io/docs/getting-started.md
- SDK (JS/TS): https://mynth.io/docs/sdks/typescript.md
- This page as JSON: https://mynth.io/models/openai%2Fgpt-image-2.json

## More from OpenAI
- GPT Image 2.5 Flare [openai/gpt-image-2.5-flare]: https://mynth.io/models/openai%2Fgpt-image-2.5-flare.md
- GPT Image 2.5 Sunburst [openai/gpt-image-2.5-sunburst]: https://mynth.io/models/openai%2Fgpt-image-2.5-sunburst.md

## Similar models
- Luma UNI-1 Max [luma/uni-1-max]: https://mynth.io/models/luma%2Funi-1-max.md
- Seedream Pro [bytedance/seedream-pro]: https://mynth.io/models/bytedance%2Fseedream-pro.md
- Qwen Image 2.1 Pro [alibaba/qwen-image-2.1-pro]: https://mynth.io/models/alibaba%2Fqwen-image-2.1-pro.md
- Qwen Image 3.0 [alibaba/qwen-image-3.0]: https://mynth.io/models/alibaba%2Fqwen-image-3.0.md
- Qwen Image 3.0 Pro [alibaba/qwen-image-3.0-pro]: https://mynth.io/models/alibaba%2Fqwen-image-3.0-pro.md