4:1 and 8:1 panorama images: only Nano Banana 2 lists them on Sume

Answer

For a native 4:1, 1:4, 8:1 or 1:8 image, Nano Banana 2 (google/nano-banana-2) is the one row in Sume's image catalog that lists those ratios on 2026-10-04. It costs $0.10 at 1K, $0.15 at 2K and $0.20 at 4K per image, and it lists 14 aspect ratios in total.

Other rows go as wide as 3:1 (Ideogram) or 21:9 (Nano Banana Pro, Flux, Qwen, Recraft). If you ask a model for a ratio it does not list, Sume answers with a 400 and does not guess.

Request

curl -X POST https://api.sume.com/v1/images \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/nano-banana-2","prompt":"a long mountain ridge at dusk, empty sky on the left","aspect_ratio":"8:1","resolution":"2K"}'

Uses and limits

• Site headers, ticker strips and footer art are the usual 4:1 and 8:1 jobs. Leave empty space in the prompt where your text will go and add the text in code.
• 1:4 and 1:8 suit tall sidebars and vertical scroll banners.
• A very wide image has few pixels on the short side. Check the output size before you promise a print or a screen width.
• A 2K render can exceed the 30-second sync wait and return a 202 job envelope. Poll the job status endpoint, then fetch the result.

If you need a ratio that no row lists, generate a nearby ratio and crop. To see what each row accepts, call GET /v1/images/models and read the aspect_ratio descriptor. Docs: Sume Image API.

Before a large run

Prices and descriptors change when the catalog changes, so confirm them before you spend. Call GET /v1/images/models/{id}/endpoints for the row you plan to use and read its pricing line and supported_parameters; both come back in one response.

Then run a pilot of three to five images and read usage.cost on each response. Multiply by your planned count for a forecast you can trust. Completed generations are billed in full and failed or cancelled ones are not, so a pilot that errors costs nothing.

For big batches, use mode: "async" or mode: "webhook" with a public HTTPS webhook_url, so no request waits on the 30-second sync limit. Poll GET /v1/jobs/{id}/status and fetch GET /v1/jobs/{id}/result when the job completes.