About this model
High speed 4K AI image generation and editing model. Seedream 4.0 is ByteDance's multimodal image model for fast 2K to 4K generation.
Pricing
| Rate | RODI | USD (ref.) | Unit |
|---|---|---|---|
| Image | |||
| Image out | 22.8 | ~ 0.03 | per image (RODI/img, USD/img) |
RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.
Providers & pricing
| Provider | Input | Output | Cached | Free tier | Status |
|---|---|---|---|---|---|
 Runware Default All rates (1)
| - | - | - | - | No data |
Capabilities
Streaming
Tool calling
Vision
JSON mode
Reasoning
API usage
Generate images with client.images(): POST /v1/images/generations.
Examples
…Example response
…Reference image (edit or restyle)
…RodiumAi SDK
images() maps to POST /v1/images/generations for this image model.
…Use cases
- Marketing visuals, social posts and ad variants from a short brief.
- Product shots and mock-ups for a catalogue.
- Illustrations for articles, slides and onboarding screens.
- Concept art and moodboards before a design review.
- Backgrounds, textures and placeholder images for apps.
Notes
- Endpoint:
POST https://api.rodiumai.io/v1/images/generations, the OpenAI Images format. Billing is per image (or per token for token-priced models, see the pricing table above). - Each item of
dataholds eitherb64_json(base64) orurl, depending on the model. Handle both, as in the examples. Hosted URLs are temporary: download the file. n(up to 10) asks for several variants in one call.sizeisWIDTHxHEIGHT, for example1024x1024,1536x1024or1024x1536. Sizes a model does not support are rejected or snapped by the model.- A reference image goes in
image, or several inimages(up to 14), as a base64 data URL or raw base64. Models served by OpenAI and Azure need inline base64, not a URL. - Describe subject, style, lighting and composition. Short, concrete prompts work better than long lists of adjectives.