Bytedance · Image

OpenClaw x Seedream

Seedream is optimized for typography and style control. Through RunAPI, all Seedream variants share one key and unified billing.

Public versions and endpoints

Model IDVersionEndpointsStarting priceCatalog
seedream-4.5-editSame realism with targeted region editing via mask/brush
/api/v1/seedream/edit_image
$0.100Model detail
seedream-4.5-text-to-imagePhotorealistic output; stable anatomy
/api/v1/seedream/text_to_image
$0.100Model detail
seedream-5-lite-editStronger reference adherence + bilingual typography vs 4.5; faster
/api/v1/seedream/edit_image
$0.080Model detail
seedream-5-lite-text-to-imageReal-time web search for time-sensitive prompts; ~15% cheaper
/api/v1/seedream/text_to_image
$0.080Model detail
seedream-5-pro-editHigh-quality photorealistic editing for polished production imagery
/api/v1/seedream/edit_image
$0.170Model detail
seedream-5-pro-layer-decompositionSplit one image into an editable base image and transparent PNG layers
/api/v1/seedream/decompose_layers
$0.140Model detail
seedream-5-pro-text-to-imageHigh-quality photorealistic generation for polished production imagery
/api/v1/seedream/text_to_image
$0.110Model detail
seedream-v4-editMulti-image editing with up to 10 references and 4K output
/api/v1/seedream/edit_image
$0.080Model detail
seedream-v4-text-to-imagePhotorealistic 1K-4K batches; up to 6 images per prompt
/api/v1/seedream/text_to_image
$0.080Model detail

Configuration

Guide endpoint: <endpoint>

Select <model-id> to generate a request with the endpoint's public input contract.

Verify

Select <model-id> to generate verification commands.

How it works

  1. 1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. 2. Configure RunAPI

    Set RUNAPI_API_KEY before making the endpoint request.

  3. 3. Verify the result

    For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.

FAQ

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.