# GPT Image 2

> GPT Image 2 is OpenAI's image model, used for both generation and editing. Its notable strengths are prompt adherence and text rendering inside the image — the second is what makes it usable for mockups, packaging and marketing collateral, where illegible in-image text would otherwise mean a separate design pass.

Canonical: https://routemux.com/openai/gpt-image-2
Provider: OpenAI

## Key facts

| Field | Value |
| --- | --- |
| Model ID | openai/gpt-image-2 |
| Official model ID | gpt-image-2 |
| Input modalities | text, image |
| Output modalities | image |
| Capabilities | Image Generation, Image Edit |
| Upstream release | 2026-04-21 |
| Availability | available |

## Pricing

- RouteMux: $0.0186 per generation
- Official: $0.062 per generation
- Saving vs official: 70%
- Official price source: official_x0.3, verified 2026-06-08

Billing is prepaid wallet, charged per successful request only.

## API access

Base URL: https://api.routemux.com

Supported protocols:

- openai_images

## What is GPT Image 2

GPT Image 2 is OpenAI's image model, used for both generation and editing. Its notable strengths are prompt adherence and text rendering inside the image — the second is what makes it usable for mockups, packaging and marketing collateral, where illegible in-image text would otherwise mean a separate design pass.

Requests to this model name are served by the newer GPT Image 2.5 Flare. Nothing in your code has to change: the model name, the endpoints and the request shape all stay the same, and you get the newer generation's output quality. If you would rather name the new model explicitly, call gpt-image-2.5-flare — or gpt-image-2.5-sunburst when edit precision matters more than speed.

Billing is per image, not per token. One image costs one fixed amount, independent of prompt length or scene complexity, so budgeting is just price times image count. Each call returns a single image; the size parameter picks the aspect ratio rather than the resolution, and the dimensions in the response are the ones that count.

It answers on the OpenAI Images protocol, so /v1/images/generations and /v1/images/edits work as they would against OpenAI directly. The image comes back as base64 in data[0].b64_json.

## Key capabilities

- **Generation and editing** — Both /v1/images/generations and /v1/images/edits route to this model.
- **Flat price per image** — One price per image, independent of prompt length or scene complexity. Budget is price times count.
- **Upgraded to 2.5 Flare** — Requests to this model name are now served by GPT Image 2.5 Flare. Same API, no code changes.
- **OpenAI Images native** — Same request shape as calling OpenAI directly.

## Other variants in this family

- GPT Image 2.5 Flare (`openai/gpt-image-2.5-flare`)
- GPT Image 2.5 Sunburst (`openai/gpt-image-2.5-sunburst`)

## Sources

- [OpenAI — Models](https://platform.openai.com/docs/models)
- [OpenAI — Pricing](https://openai.com/api/pricing/)

_Content reviewed by Jerry Fan on 2026-09-10._