
We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
bytedance/seedream-5-544 credits at 1K and 1.5K, 77 at 2K
Seedream 5.5 is ByteDance's image model for generating from text and editing from reference images. It is billed by the size you ask for: 44 credits at 1K, 44 at 1.5K, 77 at 2K. Pick the size per request, and ask for a wide range of aspect ratios, from square to 21:9.
Last updated Nov 19, 2026
Describe an image, get an image back
Send reference images and change what you want to change
1K, 1.5K and 2K, each at a fixed price
Square, portrait, landscape and ultra-wide formats
A hand-painted wooden shop sign reading "ATELIER COUTURE" in bold lettering, cobalt blue on cream, hanging above a doorway in the late afternoon light, photographic detail.
A flat vector concert poster: a large yellow circle behind the black silhouette of a kora, the words "LIVE SESSION" across the top and "SAMEDI 21H" at the bottom, three flat colours only, hard edges, no gradient and no texture.
Product photo of a glass jar of shea butter on a pale grey backdrop, a kraft paper label reading "BEURRE DE KARITE 200 g", soft studio light, shallow depth of field.
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": "seedream-5-5",
"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. `seedream-5-5`).
promptRequiredText description of the image to generate.