GGoogle · Released Jun 18, 2026
Nano Banana 2 (Gemini 3.1 Flash Image)
Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...
- Released
- Jun 18 2026
- Context window
- 131K 33K out
- Input / 1M tokens
- $0.50
- Output / 1M tokens
- $3.00 from $2.00
Where to run it
10 providers compared
Cheapest: Requesty at $0.50 / $2.00 per 1M input / output tokens — 94% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Requesty | $0.50 | $2.00 | — | 131K | 33K | — | Cheapest |
| Googleglobal · no tool calling | $0.50 | $3.00 | — | 131K | 33K | 100%24h | +29% |
| Google AI Studiono tool calling | $0.50 | $3.00 | — | 66K | 59K | 89.1%24h | +29% |
| Kilo Gatewayno tool calling | $0.50 | $3.00 | — | 131K | 33K | — | +29% |
| Vercel AI Gatewayno tool calling | $0.50 | $3.00 | $0.05 | 131K | 33K | — | +29% |
| AIHubMixno tool calling | $0.50 | $3.00 | — | 131K | 33K | — | +29% |
| Abacusno tool calling | $0.50 | $3.00 | — | 1M | 33K | — | +29% |
| Merge Gatewayno tool calling | $0.50 | $3.00 | — | 33K | 33K | — | +29% |
| Eden AIno tool calling | $0.50 | $3.00 | — | 131K | 33K | — | +29% |
| Googleus · no tool calling | $0.55 | $3.30 | — | 131K | 33K | — | +41% |
| Vertexno tool calling | $0.50 | $60.00 | $0.05 | 131K | 33K | — | +1657% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Nano Banana 2 (Gemini 3.1 Flash Image). Scores appear here automatically once it does.
Specs
Details
- Model ID
google/gemini-3.1-flash-image- Developer
- Release date
- Jun 18, 2026 ·
- Context window
- 131,072 tokens
- Max output
- 32,768 tokens
- API price
- $0.50 / $3.00 per 1M input / output tokens
- Providers
- 10
- Input types
- image, text
- Reasoning
- Yes
- Tool calling
- No
- Open weights
- No
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.