Seedream 5.5 API
Generate and edit Seedream 5.5 images from your own code. One endpoint covers both: send a prompt for text-to-image, or add up to 10 image_urls to edit or compose. Pick 1K, 1.5K or 2K, an aspect ratio, png or jpeg, and set background to transparent for a PNG with an alpha channel. Each request is priced across the providers that serve the model and runs on the cheapest one.
20% less than the priciest provider (2 compared). Same model, same output.
As of , Seedream 5.5 costs from $0.016 per image on Scenetra, billed at provider cost with no markup. Each run is priced across 3 providers and runs on the cheapest one that supports your settings.
- 1K
- $0.016
- 1.5K
- $0.016
- 2K
- $0.028
- Each input image (edits)
- +$0.0064
Quickstart
Async by design: submit a generation, get a run id back instantly, poll until it completes (or pass a callbackUrl).
1 — Start a generation
curl -X POST https://app.scenetra.com/api/v1/generate/seedream55 \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"a ceramic coffee mug with a hand-painted fox, studio product shot","aspect_ratio":"1:1","resolution":"1.5K","background":"transparent"}'Response (202)
{
"runId": "run_abc123",
"status": "PENDING",
"model": "seedream55",
"estimatedCredits": 16,
"statusUrl": "/api/v1/runs/run_abc123"
}2 — Poll until COMPLETED (every 2-5 seconds)
curl https://app.scenetra.com/api/v1/runs/run_abc123 \
-H "Authorization: Bearer YOUR_API_KEY"Response
{
"runId": "run_abc123",
"status": "COMPLETED",
"progress": { "completed": 1, "total": 1 },
"outputs": [
{ "type": "image", "url": "https://images.scenetra.com/..." }
],
"error": null,
"estimatedCredits": 16
}Request fields
| Field | Type | Description | Default |
|---|---|---|---|
| prompt* | string | Describe the image to generate, or the edit to apply to the input images. | — |
| image_urls | string[] (https URLs) | Optional images to edit or compose from (up to 10). Leave empty for pure text-to-image. Each input image adds a small fee. | — |
| aspect_ratio | string | Aspect ratio of the output image. 'auto' follows the first input image where supported.auto · 21:9 · 16:9 · 3:2 · 4:3 · 1:1 · 3:4 · 2:3 · 9:16 | 1:1 |
| resolution | string | Output resolution tier. 1K and 1.5K cost the same; 2K costs more.1K · 1.5K · 2K | 1.5K |
| output_format | string | Image file format. A transparent background needs png.png · jpeg | png |
| background | string | 'auto' lets the model decide from your prompt. 'transparent' returns a PNG with an alpha channel (cut-outs, stickers, product shots).auto · transparent · opaque | auto |
| callbackUrl | string (https URL) | Optional. When the run finishes (completed or failed), we POST the final run status to this URL — same shape as the poll response, plus model, params, and chargedCredits. Best-effort; polling remains the source of truth. | |
Unknown fields are rejected with a helpful 400. Media fields take https URLs. There is no provider parameter — every run is routed to the cheapest capable provider automatically.
Good to know
Billing
Runs bill your account credits at provider cost with 0% markup. The submit response includes the credit estimate; failed generations are refunded automatically. Add ?dryRun=1 to get the estimate without running anything.
Errors
Errors are always { "error": { "code", "message" } } with stable codes: unauthorized, model_not_available, invalid_parameter, insufficient_credits, rate_limited. A failed run is not an HTTP error — poll responses report status: "FAILED" with the reason.
Seedream 5.5 API FAQ
How do I get a transparent background?+
Set background to transparent and leave output_format on png. The image comes back with an alpha channel. It works on text-to-image and on edits.
How do I edit an image instead of generating one?+
Add image_urls with one to ten https URLs and describe the change in prompt. The same endpoint handles both. Each input image adds a small fee to the run.
Is this the official ByteDance API?+
No. Scenetra routes each call to a provider that serves Seedream 5.5 (the same model and output) and bills you in Scenetra credits from one balance.
How much does the Seedream 5.5 API cost?+
As of November 10, 2026, Seedream 5.5 costs from $0.016 per image on Scenetra, billed at provider cost with no markup. Each run is priced across 3 providers and runs on the cheapest one that supports your settings. Rates: 1K $0.016; 1.5K $0.016; 2K $0.028; Each input image (edits) +$0.0064. With default settings (1.5K), a run is estimated at about 16 credits. The submit response returns the estimate for your exact settings, and adding ?dryRun=1 prices a request without running it.
Which provider runs my request?+
The cheapest one that supports your settings, chosen per request. There is no provider parameter: the same Seedream 5.5 request is priced across every provider we route to and runs on the lowest quote.
Do failed generations cost credits?+
No. Credits are reserved when you submit and refunded automatically if the run fails. A failed run is not an HTTP error: polling returns status FAILED with the reason.
Do I have to poll, or can I get a webhook?+
Both work. Pass callbackUrl and we POST the final run status to it when the run completes or fails. Delivery is best-effort, so polling GET /api/v1/runs/{runId} remains the source of truth.