by Google DeepMind
Google: Nano Banana 2.1.
multimodal
closed
66K ctx
Cheapest input
$1.5/M
on OpenRouter
Cheapest output
$7.5/M
on OpenRouter
Hosted equiv.
~$2.7/hr
@ 100 tok/s on OpenRouter
Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...
Hosted API only
No self-host path — closed weights.
Google: Nano Banana 2.1's weights aren't published. Use it via the access providers below.
Where to use it
Cheapest hosted endpoints.
| Provider | Access | $/M in | $/M out | |
|---|---|---|---|---|
| OpenRouter | api aggregator | $1.5 | $7.5 | Launch ↗ |
FAQ
Frequently asked.
How do I run Google: Nano Banana 2.1?
Google: Nano Banana 2.1 is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access Google: Nano Banana 2.1?
Google: Nano Banana 2.1 is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Google: Nano Banana 2.1?
API pricing starts at $1.5/M input tokens and $7.5/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Google: Nano Banana 2.1 open-source or proprietary?
Google: Nano Banana 2.1 is a proprietary model from Google DeepMind. Access is API-only — there are no public weights to download.
API pricing
Per provider
What it costs per month across providers.
Estimate your monthly bill for Google: Nano Banana 2.1 across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest
$30.0
OpenRouter
$/M input
$1.5
per million tokens
$/M output
$7.5
per million tokens
Providers
1
with priced rows
Monthly bill
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Loading...
Bill breakdown.
| Provider | Monthly total | |
|---|---|---|
| $30.0 | Sign up ↗ |
Full calculator
Want to compare token volumes across other models too?
Open the standalone API pricing tool →
Context window
How much it can remember.
66K tokens
≈ 49,152 English words
4K
32K
128K
1M
Capabilities
What it can do.
·
Vision input
·
Audio input
·
Video input
·
Function calling
·
Tool use
·
JSON mode
✓
Streaming
·
Fine-tuning