Type
Spec
Rate
Output up to 2.61MP
per image
$0.0332
Output above 2.61MP
per image
$0.0581
Input image
per input image
$0.0133
Seedream 5.5 and Seedream 5.0 Pro side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
ByteDance Image GenerationSeedream 5.5 and Seedream 5.0 Pro are both ByteDance models in the Image Generation category, available through the EmpirioLabs API.
| Spec | Seedream 5.5 | Seedream 5.0 Pro |
|---|---|---|
| Model ID | seedream-5-5 | seedream-5-0-pro |
| Author | ByteDance | ByteDance |
| Released | Nov 9, 2026 | Jul 8, 2026 |
| Input | Text Image | Text Image |
| Output | Image | Image |
| Region | Malaysia | Malaysia |
| Endpoints | POST /v1/images/generations | POST /v1/images/generations |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Seedream 5.5 | Seedream 5.0 Pro |
|---|---|---|
| prompt | string | string |
| image | array | array |
| images | array | array |
| aspect_ratio | auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 Default: auto | auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 Default: auto |
| layer_decomposition | boolean Default: false | boolean Default: false |
| max_images | 2 to 100 Default: 30 | - |
| text_recognition | boolean Default: false | - |
| quality | 1K, 1.5K, 2K Default: 2K | 1K, 1.5K, 2K Default: 2K |
| size | string | string |
| use_custom_size | boolean Default: false | boolean Default: false |
| custom_width | 15 to 8600 | 15 to 8600 |
| custom_height | 15 to 8600 | 15 to 8600 |
| watermark | boolean Default: false | boolean Default: false |
| output_format | jpeg, png Default: png | jpeg, png Default: png |
| background | auto, transparent, opaque Default: auto | opaque, transparent Default: opaque |
| response_format | url, b64_json Default: url | url, b64_json Default: url |
Mark the region to change directly on the input image with a sketch, circle, or arrow, then describe it in the prompt. For exact placement, use coordinate tags on a 0 to 1000 normalized grid:
Place the subject from image 1 <bbox>179 283 796 986</bbox> at the position in image 2 <bbox>118 331 933 871</bbox>.Set layer_decomposition to true with exactly one input image to split it into a base image plus up to 99 transparent PNG layers. max_images sets the most images returned, the base image included, from 2 to 100, and defaults to 30; a higher value allows a finer decomposition. Every returned image carries its stacking order as z_index, and each layer also carries its position in the base image as bounding_box.absolute and bounding_box.normalized, plus a name and a description. Scale each layer to its box when you reassemble the image. Leave the prompt empty to let the model choose the elements, or name the elements or coordinate regions to separate. Resolution accepts 1K, 1.5K, or 2K, and matches the input image when unset.
With text_recognition on, each regular text layer also returns text_recognition: its full text, the position of each line, and the styling of each run of text (a similar font, color, bold, italic, underline, strikethrough, shadow, and translucency). Artistic text and handwriting are not recognized.
background defaults to auto, which lets the model decide from the prompt and output format. Transparent returns an image with an alpha channel, from text alone or from up to 10 reference images that need no alpha channel, and requires PNG output. Opaque returns an image without one. Each returned image reports its actual transparency as background. Layer decomposition does not take background, and its layers are always transparent PNG.
Each returned image bills at its own size: up to 2.61MP, which covers 1K and 1.5K, or above 2.61MP, which covers 2K. Every input image bills, the one for layer decomposition included. Layer decomposition bills every returned image, the base image and each layer, at its own size.
Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.
Mark the region to change directly on the input image with a sketch, circle, or arrow, then describe it in the prompt. For exact placement, use coordinate tags on a 0 to 1000 normalized grid:
Place the subject from image 1 <bbox>179 283 796 986</bbox> at the position in image 2 <bbox>118 331 933 871</bbox>.Set layer_decomposition to true with exactly one input image to split it into a base image plus up to 16 transparent PNG layers. Every returned image carries its stacking order as z_index, and each layer also carries its position in the base image as bounding_box.absolute and bounding_box.normalized, plus a name and a description. Leave the prompt empty to let the model choose the elements, or name the elements or coordinate regions to separate. Resolution accepts 1K, 1.5K, or 2K, and matches the input image when unset.
Layer decomposition bills every returned image, the base image and each layer, at half the standard per-image rate, tiered on the pixel count of that image.
Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.
Seedream 5.5 runs through POST /v1/images/generations. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Or add "sync": true to skip polling: the request stays open and returns the finished OpenAI-style image response directly, so OpenAI SDKs work as-is. Both models are called through the same endpoint. Set model to seedream-5-5 or seedream-5-0-pro. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/images/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream-5-5",
"prompt": "Describe what you want Seedream 5.5 to generate."
}'Prompt tests and comparison runs that cover both models.
Seedream 5.5 is the newer release (Nov 9, 2026); Seedream 5.0 Pro was released on Jul 8, 2026. Seedream 5.5 lists the lower rate for Output up to 2.61MP (per image) and Output above 2.61MP (per image). The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Seedream 5.5 is the newer release (Nov 9, 2026); Seedream 5.0 Pro was released on Jul 8, 2026.
Seedream 5.5 lists the lower rate for Output up to 2.61MP (per image) and Output above 2.61MP (per image). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/images/generations with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.
