Nano Banana Google Search grounding: not a Sume parameter
Google documents Search grounding for its Gemini image models. Sume lists Nano Banana 2 but no grounding field, and unlisted fields return 400.

Grounding with Google Search is a feature of Google's own Gemini image API. Sume's image request has no grounding field, so you cannot switch it on through google/nano-banana-2: a parameter the model does not list returns 400 unsupported_parameter.
Google's feature list is from its image generation page; Sume's rules are from Image generation and editing and the image catalog code, read 2026-09-30.
What does Google document?
The page says the model can use Google Search as a tool to verify facts and generate imagery from real-time data, with examples such as weather maps, stock charts and recent events. It says Gemini 3.1 Flash Image adds Google Image Search grounding alongside web search, and that the Gemini 3.1 Flash Lite Image model does not support Search grounding.
What does Sume list for Nano Banana?
| Topic | Sume |
|---|---|
| Model in catalog | google/nano-banana-2, edit-capable |
| Grounding or tools field | None listed in the docs |
| Unlisted field | 400 unsupported_parameter |
stream | 400 streaming_not_supported until native SSE ships |
How can I check what a model accepts?
Use the model discovery route, which returns supported_parameters per model; that is the definitive list. If a field is not there, do not send it.
What can I do if my image needs current facts?
Fetch the facts in your own code or agent, put them in the prompt, and then generate. Sume will render what the prompt says; it does not look anything up. For other Nano Banana request rules see the quality parameter.
Sources
Related posts
More in Models
- Nano Banana Pro aspect ratio: auto keeps the reference shape
Freepik's changelog says Nano Banana Pro accepts aspect_ratio auto to follow reference images; omitting it stays 1:1. On Sume, omitting is also not auto.
- Nano Banana thinking mode and thought images on Sume
Google's Gemini 3 image models use thinking mode and uncharged thought images. Sume lists no thinking field, and you pay only for completed images.
- Odia and Urdu text to speech API: the language codes
Cartesia's Sonic 3.6 adds Odia (`or`) and Urdu (`ur`). On Sume, send the code in `language`, pin `sonic-3.6`, and check the voice before you pay.
- OmniHuman 1.5 API: native 1080p vs Sume avatar 720p
BytePlus says OmniHuman 1.5 outputs native 1080p from one image plus audio. Sume's Avatar Video currently outputs 720p; its video models list 1080p separately.
Written by Sume