Seedream · 5.0 Lite
Create an image
Enable JavaScript to use the playground.
MODEL GUIDE
Build with Seedream
Create an image with Seedream · 5.0 Lite. Try its settings in the playground and copy the same request into your application.
How to use this model
- Choose create an image and adjust the settings above.
- Add the input media required by your task. Use a public URL or a media ID from your account.
- Run the request, review the result, then copy the API code.
One request, any integration
Send POST /api/v3/run with model: seedream/5.0-lite. The API returns the run ID and expected cost. Read GET /api/v3/run/{id} for its status and result URLs, or provide a webhook URL.
In MCP, use run with the same model and parameters.
Parameters
These fields come from this model’s API schema. The server also validates input combinations and conditional limits.
| Parameter | Type | Values / default |
|---|---|---|
n | integer | 1 |
size | string | 1K · 2K · 3K · 4K · 648x1512 · 720x1280 · 832x1248 · 864x1152 · 1024x1024 · 1152x864 · 1248x832 · 1280x720 · 1512x648 · 1296x3024 · 1440x2560 · 1664x2496 · 1728x2304 · 2048x2048 · 2304x1728 · 2496x1664 · 2560x1440 · 3024x1296 · 1944x4536 · 2160x3840 · 2496x3744 · 2592x3456 · 3072x3072 · 3456x2592 · 3744x2496 · 3840x2160 · 4536x1944 · 2592x6048 · 2880x5120 · 3328x4992 · 3456x4608 · 4096x4096 · 4608x3456 · 4992x3328 · 5120x2880 · 6048x2592 |
prompt | string | Optional; validated by the model |
negative_prompt | string | Optional; validated by the model |
image_references | array | Up to 64 references |
webhook_url | string | Public HTTPS destination for this Run. No registration required. Deliveries use Ed25519 signatures; public keys: /.well-known/jwks.json. |
How do billing and results work?
Estimate the current request with POST /api/v3/run/estimate before generating. Generations use your Fusara balance. A successful run includes direct output URLs; save results you need before their links expire. An estimate does not create a run.
Can I use this model from an agent?
Connect your client to https://fusara.ai/mcp. Use get_model to discover the current schema, estimate_run for the expected cost, and run to start.