flux-2-pro-preview vs flux-2-pro: which id does Sume send?
BFL has flux-2-pro-preview (latest) and flux-2-pro (fixed snapshot). Sume lists black-forest-labs/flux.2-pro and does not let you pick the BFL endpoint.

On Sume you send black-forest-labs/flux.2-pro, and you cannot choose between BFL's flux-2-pro-preview and its fixed flux-2-pro snapshot. BFL's FLUX.2 overview describes the preview endpoint as its latest FLUX.2 [pro] model and the non-preview endpoint as a snapshot that will not change. Sume's Image API page says it serves each catalog model through one sume endpoint and does not disclose the upstream provider, so the docs do not say which BFL endpoint sits behind the id.
BFL's text is from its FLUX.2 overview, read 2026-10-02. Sume's is from the Sume Image API page, read the same day.
What is the difference on BFL's side?
BFL says preview endpoints are where its latest improvements land first. It lists flux-2-pro-preview (latest FLUX.2 [pro]), flux-2-pro (a fixed snapshot, "suitable for workflows that require reproducibility"), flux-2-klein-9b-preview and flux-2-klein-9b. It also says both kinds share one API contract: the request and response format is identical and only the model weights differ.
| BFL endpoint | What BFL says | Sume catalog id |
|---|---|---|
| flux-2-pro-preview | Latest FLUX.2 [pro] | Not listed separately |
| flux-2-pro | Fixed snapshot of FLUX.2 [pro] | black-forest-labs/flux.2-pro |
| flux-2-klein-9b-preview | Latest klein 9B, with KV caching | Not listed |
| flux-2-klein-9b | Fixed snapshot of klein 9B | Not listed |
Can I pick the endpoint through Sume?
No parameter does it. Sume's docs say allowed_passthrough_parameters is empty for every endpoint in v1, so provider.options must be omitted or empty, and that multi-provider routing fields are accepted but inert. Any provider slug other than sume returns 400 provider_not_available.
What should I do if I need reproducible FLUX.2 images?
Treat the Sume id as the contract you have. Save the image URL and the job result you got, rather than assuming a later call reproduces it. Sume also does not serve a seed: it is in the schema, but no model advertises it, and sending one returns 400 unsupported_parameter.
If reproducibility from BFL's own snapshot matters to you more than going through one Sume API, that is a reason to call BFL directly. Sume's docs do not claim the snapshot behind its id.
Sources
Related posts
More in Models
- gemini-omni-1.1-flash vs gemini-omni-flash-1.1: which id goes where
Google writes the model id gemini-omni-1.1-flash; Sume's catalog id is gemini-omni-flash-1.1. A mapping table, the old preview id, and how to avoid a typo.
- Gemini Omni audio reference: unsupported; Sume models that take audio
Google says Omni's API doesn't accept uploaded audio references. Sume's Omni row has no reference_audio_urls; Seedance 2.x, Wan 3.0 and MiniMax H3 honor audio.
- Gemini Omni extend: no new dialogue on an uploaded talking clip
Google says you can't extend an uploaded Omni clip where someone talks to add dialogue; extension only appends, to clips up to 10 s. Sume lists no extend mode.
- Gemini Omni with several videos: 3 references, no cross-video use
Gemini Omni takes up to 3 reference clips of 3 s each, yet Google warns that reasoning across several videos may degrade output. Sume: one video_url source.
Written by Sume