GGoogle · Released Jun 18, 2026
Nano Banana Pro (Gemini 3 Pro Image)
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
- Released
- Jun 18 2026
- Context window
- 131K 33K out
- Input / 1M tokens
- $2.00
- Output / 1M tokens
- $12.00
Where to run it
10 providers compared
Cheapest: Google, Google AI Studio, Kilo Gateway +5 more at $2.00 / $12.00 per 1M input / output tokens — 86% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Googleglobal · no tool calling | $2.00 | $12.00 | $0.20 | 66K | 33K | 100%24h | Cheapest |
| Google AI Studioglobal | $2.00 | $12.00 | $0.20 | 131K | 33K | 98.7%24h | Cheapest |
| Kilo Gateway | $2.00 | $12.00 | $0.20 | 66K | 33K | — | Cheapest |
| Vercel AI Gatewayno tool calling | $2.00 | $12.00 | $0.20 | 66K | 33K | — | Cheapest |
| Requesty | $2.00 | $12.00 | $0.20 | 1M | 33K | — | Cheapest |
| Abacusno tool calling | $2.00 | $12.00 | $0.20 | 66K | 33K | — | Cheapest |
| Merge Gatewayno tool calling | $2.00 | $12.00 | — | 66K | 66K | — | Cheapest |
| Eden AIno tool calling | $2.00 | $12.00 | $0.20 | 66K | 33K | — | Cheapest |
| AIHubMixno tool calling | $2.00 | $120.00 | — | 66K | 33K | — | +600% |
| Vertexno tool calling | $2.00 | $120.00 | $0.20 | 66K | 33K | — | +600% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Nano Banana Pro (Gemini 3 Pro Image). Scores appear here automatically once it does.
Specs
Details
- Model ID
google/gemini-3-pro-image- Developer
- Release date
- Jun 18, 2026 ·
- Context window
- 131,072 tokens
- Max output
- 32,768 tokens
- API price
- $2.00 / $12.00 per 1M input / output tokens
- Providers
- 10
- Input types
- image, text
- Reasoning
- Yes
- Tool calling
- Yes
- 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.