Replicate API exposes Seedream 5.0 Pro through model ID bytedance/seedream-5-pro. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-17. Next refresh: weekly.
Quick Start
- 1
- 2Use the Replicate API SDK or REST API to call
bytedance/seedream-5-pro— see the documentation for request format.
Code Examples
pip install replicateREPLICATE_API_TOKENbytedance/seedream-5-proReplicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
import replicate
# reads REPLICATE_API_TOKEN from env
# bytedance/seedream-5-pro format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"bytedance/seedream-5-pro",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Pricing on Replicate API
Capabilities
About Seedream 5.0 Pro
Seedream 5.0 Pro is ByteDance Seed's multimodal image generation and editing model, officially launched 2026-07-08. It does text-to-image, single and multi-image-to-image, interactive editing guided by boxes, points, arrows and sketches, layer decomposition (1 base image plus up to 16 layers), and native multilingual text rendering. Output resolutions are 1K, 1.5K and 2K. Proprietary API model: Volcengine Ark doubao-seedream-5-0-pro-260628, BytePlus ModelArk dola-seedream-5-0-pro-260628.