Seedream 5.0 Flash: which Seedream 5 id Sume's catalog lists
Higgsfield added Seedream 5.0 Flash on Sep 23, 2026. Sume's image catalog lists seedream-5-lite and no Flash id. Check GET /v1/images/models before calling.

Higgsfield's changelog added Seedream 5.0 Flash on Sep 23, 2026. Sume's image catalog, as read 2026-10-01, lists bytedance-seed/seedream-5-lite for the Seedream 5 family and has no Flash id, so call GET /v1/images/models to see what is live before you code against a name.
What did Higgsfield announce?
The changelog describes Seedream 5.0 Flash as a fast image model with visual reasoning, in 1K, 1.5K and 2K resolution, with multi-reference input that blends style in one frame, and generation plus editing in one model. It is offered inside Higgsfield's own model selector.
What does Sume list for Seedream 5?
The catalog maps bytedance-seed/seedream-5-lite to the router id seedream-5-lite. The docs say the bare Image Router ids are accepted as aliases for their org/slug equivalents. See the Image API docs.
| Name | Source | Resolution stated |
|---|---|---|
| Seedream 5.0 Flash | Higgsfield changelog | 1K, 1.5K, 2K |
bytedance-seed/seedream-5-lite | Sume catalog | Tiers 512, 1K, 2K, 4K are the normalized set; each model lists its own |
How do I check before calling?
Sume publishes the parameters each model accepts as capability descriptors, and a request that sets an unlisted parameter is rejected with 400 unsupported_parameter. A 1.5K request has no tier on Sume: the normalized resolution values are 512, 1K, 2K and 4K. Read the descriptor for seedream-5-lite and pin only what it lists.
Can I let Sume choose?
model: "sume/auto" lets Image Router pick, but Sume never discloses which family ran, so it is not a way to request Seedream specifically. For the related Pro question see Seedream 5.0 Pro on Sume.
Sources
Related posts
More in Models
- Speechmatics Linden for voice agents vs Sume batch STT jobs
Speechmatics announced Linden for voice agents. Sume STT is a bounded batch job with a webhook, not a live stream, so live agents need streaming.
- Synthesia Interactive Avatar API vs Sume rendered avatar clips
Synthesia headlines a live Interactive Avatar API. Sume avatar video is script-driven and rendered as a job: submit, poll, then fetch the clip.
- Vidu Q2 Pro Fast image-to-video 1080p vs Sume first frame
QwenCloud lists vidu/viduq2-pro-fast_img2video at 720P and 1080P. Sume has no Vidu id; send image_url as the first frame to a 1080p model.
- Vidu Q3 ad reference-to-video vs Sume reference images
QwenCloud lists a Vidu Q3 ad reference-to-video model. Vidu is not in Sume's video ids; reference images work on models that list them.
Written by Sume