Gemini 3.1 flash image preview shutdown: Sume model ids
Google lists gemini-3.1-flash-image-preview and gemini-3-pro-image-preview for June 25, 2026 shutdown. Sume callers use catalog ids like google/nano-banana-2.

Google's deprecations page lists gemini-3.1-flash-image-preview and gemini-3-pro-image-preview with a June 25, 2026 shutdown date, and names gemini-3.1-flash-image and gemini-3-pro-image as the replacements. Calls through Sume do not use those ids: you send a catalog id such as google/nano-banana-2.
What does Google's deprecations page say?
The page defines a shutdown as the model being completely turned off, with the endpoint no longer available. It lists the two preview image ids below.
| Preview id | Shutdown date | Replacement |
|---|---|---|
gemini-3.1-flash-image-preview | June 25, 2026 | gemini-3.1-flash-image |
gemini-3-pro-image-preview | June 25, 2026 | gemini-3-pro-image |
Which id do I use on Sume?
Sume's image catalog lists google/nano-banana-2, and the bare router id nano-banana-2 is accepted as an alias for it. Sume serves every catalog model through a single sume endpoint in v1, and GET /v1/images/models shows what is available. See the Image API docs.
Do I have to migrate anything on Sume?
If your Sume code already sends a catalog id, nothing here names a preview id to change. If a script still carries a Gemini preview string in a model field, replace it with a catalog id from GET /v1/images/models. Related: the earlier Gemini 2.5 Flash Image shutdown.
What if I do not care which family runs?
model: "sume/auto" lets Sume pick the family and never discloses which one ran, so use a catalog id when you need a specific model.
Sources
Related posts
More in Models
- Veo 3.1 Lite preview shuts down Oct 22: Omni Flash on Sume
Google lists veo-3.1-lite-generate-preview shutting down October 22, 2026 with gemini-omni-1.1-flash as replacement. Sume id: gemini-omni-flash-1.1.
- GPT Image aspect ratios for a Pinterest pin (2:3) and Instagram (4:5)
Sume lists 17 aspect ratios, including 2:3 for a Pinterest pin and 4:5 for an Instagram portrait. A model only accepts the ratios its catalog row lists.
- Grok Imagine Video 1.5 text-to-video at 1080p: xAI vs Sume
xAI lists native 1080p text-to-video for grok-imagine-video-1.5. Sume's row is image-to-video only at 480p and 720p. How the two differ and what to send.
- HappyHorse 1.0 API: what Runway lists and how to check Sume's models
Runway lists HappyHorse 1.0 at 3-15 seconds, 720p and 1080p. Sume's video docs name no such id, so read /v1/videos/models before you plan around it.
Written by Sume