ChatGPT Images 2.0

OpenAI's previous-generation model for complex images: it follows long instructions, multi-object composition, and multilingual in-frame text with high precision. Use it for infographics, slides, packaging, multilingual posters, and full-image edits in 1K, 2K, or 4K.

Cost

from 1 tokens

ImageProvider: OpenAI

Try ChatGPT Images 2.0 in Givon AI

Open a working project for regular creation, or use Playground to inspect the model parameters.

Use through API

Request fields, constraints, and ready-to-use examples for developers. The user workflow starts above.

Run generation
IDEMPOTENCY_KEY="${IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"image","model":"gpt-image-2","input":{"prompt":"studio portrait of a red corgi, soft light","aspectRatio":"9:16","quality":"low","imageSize":"1k","sourceImage":"asset://asset_...","referenceAssetUris":["asset://asset_..."]}}'

Input fields

* required
prompt*prompt

Image description.

Type
string
Default
Allowed
up to 20000 chars
aspectRatioaspectRatio
Type
string
Default
9:16
Allowed
16:9, 1:1, 21:9, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16
qualityquality
Type
string
Default
low
Allowed
low, medium, high
imageSizeimageSize
Type
string
Default
1k
Allowed
1k, 2k, 4k
Source imagesourceImage

Asset used as the source image for image editing.

Type
string
Default
Allowed
image · asset, https, data
Mask imagemaskImage

Optional mask image for region editing. Requires sourceImage.

Type
string
Default
Allowed
image · asset, https, data
Reference imagesreferenceAssetUris

Optional reference images as asset:// URIs, HTTPS URLs, or data URIs.

Type
array
Default
Allowed
image · up to 16 · asset, https, data

Cost

from 1 tokens
Low · 1K1 tokens
Low · 2K1.5 tokens
Low · 4K3 tokens
Medium · 1Kdefault2.5 tokens
Medium · 2K3.5 tokens
Medium · 4K6 tokens
High · 1K12 tokens
High · 2K14 tokens
High · 4K22 tokens

The variant is selected automatically from request fields, so you do not need to send it.

Capabilities

Modestext_to_imageimage_edit
Asset slotssourceImage:imagemaskImage:imagereferenceAssetUris:image[]<=16
Get API key

Where to use this model