Cheaper Inference
Model record / Google
gemini-nano-banana-2.1 is available for image generation from Google. Its reported context window is 131,072 tokens, with up to 32,768 output tokens. Reported inputs: image, text. The served catalog lists image input, image editing.
Ready when you are
Marketplace pricing, capped at list, optimized further.
POST /v1/images/generations
curl https://api.cheaperinference.com/v1/images/generations \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "n": 1, "model": "gemini-nano-banana-2.1", "prompt": "Render a picture of a red balloon." }'POST /v1/images/edits
curl https://api.cheaperinference.com/v1/images/edits \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "n": 1, "model": "gemini-nano-banana-2.1", "prompt": "make the background white", "input_references": [ "data:image/png;base64,<your image>" ] }'Capability source · checked
$0.2184 estimated at displayed rates
10 × $0.02184
The same billed quantities at the listed reference rates: $0.336.
Output-unit charges only. Input tokens, source media, quality settings, and other separately billed dimensions are excluded. Compare identical output settings.
Price quote effective .
| Model | Current pricing | Context limit | Image input listed |
|---|---|---|---|
| gemini-nano-banana-2.1 (this model)Google | $0.02184 / image | 131,072 tokens | Yes |
| gemini-3.1-flash-lite-imageGoogle | $0.0289 / image | 65,536 tokens | Yes |
| gemini-2.5-flash-imageGoogle | See model pricing | 32,768 tokens | Yes |
| gemini-3.1-flash-image |
This model takes the fields in its sample request. It has no other stated parameters.
See how much this model saves and when its recorded price has been lowest.
This model averaged 26.3% below comparable direct provider prices across the selected range. Its strongest observed window was 12:00 AM–10:00 AM in UTC.
Average saved
26.3%
Cheapest time
12:00 AM–10:00 AM
Hourly coverage
23/24
Signal quality
Growing
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
#146
of 332 ranked models
Last 7 days
#140
of 389 ranked models
Last 30 days
#161
of 400 ranked models
| See model pricing |
| 131,072 tokens |
| Yes |