GPT Image 2 Beta

Billed per image · lower price. Generate first, then decide if you need full settings.

Beta uses fixed settings and one image per request. Use it to try composition, style and prompts before opening the full quality tiers.

Just launched

Twelve image lines

Nano Banana, Seedream, Grok, Qwen, and GPT Image are all here. Open a card for that model's page.

Seedream 5 Pro

Grow a scene from a seed

Scene-first. Up to 10 reference images. 1K/2K. Grows a full frame from one point.

Need a scene that grows? Switch to Seedream.

SeedreamPer image1K/2K

Qwen Image 2.1

Ink with modern light

Qwen image gen. Up to 10 reference images. Ink-wash, Chinese style, and modern light.

Need ink-wash plus modern light? Switch to Qwen.

QwenPer image1K/2K

GPT Image 2

Official settings

Official API. Quality, size and count are all adjustable. For production images.

Need control and stability? This one.

OfficialQualityStable

Specs

Fixed settings, billed per image

No quality picker, no resolution picker, no batch. Put the work into the prompt.

Model ID
gpt-image-2-beta
Billing
Per image
Count
Always 1
Quality / size
Fixed, not exposed
01

Cheaper

For lots of trials. Stay on Beta while the prompt is still moving.

02

Simpler

No quality or 2K/4K picker. Send it and get an image.

03

Upgradeable

When the composition is right, switch to Image 2 or 2.5 for quality and count.

Into your workflow

Use GPT Image 2 Beta now

Generate in the dashboard, or take the same Model ID into the API.

1Web

Open AI image gen

Pick this model in the dashboard, write a prompt, and generate.

2Connect

Set endpoint and model

OpenAI-compatible API. Paste the exact Model ID.

https://api.aicodewith.ai/v1
3Make it real

Send the first request

Model ID: gpt-image-2-beta

gpt-image-2-beta
Quickstart
Need the full API notes?
Open the image API page for the parameter table and sample calls.
Open API page