We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
openai/gpt-image-2Images with readable text that follow your brief
GPT Image 2 is OpenAI's image generation and editing model, launched on 21 April 2026, following GPT Image 1 and 1.5 in the line.
OpenAI highlights better multilingual text rendering, structured generation (diagrams, infographics, charts, posters, comics) and more reliable instruction following. On Tchavi: three formats (square, portrait, landscape), three quality levels and reference images to edit or keep a style.
On Tchavi you pay with mobile money, no card and no KYC. One API key opens 80+ models, images and video included: compare GPT Image 2 with the others on the same prompt.
Improved multilingual text rendering, per OpenAI
Structured generation: diagrams, charts, comics
More reliable on detailed prompts, per OpenAI
Start from an image to edit it or keep a style
1024×1024, 1024×1536 and 1536×1024
low to iterate, medium and high for the final render
Concert poster for the "Nuits de Cotonou" festival, 18 and 19 March, with a large legible title, three lines of programme and a wax-print pattern background.
Vertical infographic in 4 steps: how to pay with mobile money and get an API key. Simple icons, short French text, lime and black palette.
Isometric illustration of a bustling West African market at golden hour, colourful stalls, signs legible in French.
GPT Image 2 is the newer of the two and the one to try first for new work. Keep GPT Image 1.5 only to reproduce an existing look.
Mini is for iterating fast on a prompt. Move to GPT Image 2 when on-image text, layout or fidelity to the brief matter for the final render.
They come from different vendors. With one Tchavi key, send the same prompt to both and keep the render that suits your use.
Three formats: 1024×1024, 1024×1536 and 1536×1024. Three quality levels: low, medium and high.
Yes: GPT Image 2 accepts reference images to edit a picture or keep a style, alongside the text prompt.
With your Tchavi API key, request an image generation with model: "gpt-image-2", your prompt, and the format and quality you want.
Yes. Top up your Tchavi account with Orange Money, MTN MoMo, M-Pesa or another mobile money operator. No bank card is needed. Credits land as soon as the payment is confirmed and are deducted as you use them.
Yes. Keep your current OpenAI SDK, just change the base URL to Tchavi's (shown in the API tab) and use your Tchavi key. The rest of your code stays the same.
import Tchavi from '@tchavi/sdk';
const client = new Tchavi({ apiKey: 'API_KEY' });
const result = await client.images.generations.create({
"model": "gpt-image-2",
"prompt": "A cute cat wearing a space suit",
"n": 1,
"quality": "standard",
"size": "1024x1024"
});
console.log(result.data[0].b64_json);
console.log('Credits used:', result.tchavi.credits_used);Every parameter this model accepts on the API. Check the SDK for full typings.
modelRequiredID of the image model (e.g. `gpt-image-2`).
promptRequiredText description of the image to generate.
n1Number of images to generate (1–4).