Nano Banana Pro (Gemini 3 Pro Image)
Google · Image generation · Released Jun 2026
Google's multimodal model for processing text and images, built on the Gemini 3 architecture with a 65K token context window.
- Strengths
- Handles both text and image inputs efficiently within a compact footprint suitable for resource-constrained deployments.
- Best for
- Multimodal workloads that require image understanding alongside text processing where context window size is not a limiting factor.
- Limitations
- The 65K token context window is smaller than newer Google models like Nano Banana 2, limiting its usefulness for processing longer documents or conversations that require extended context.
Input / 1M
$2.00
Output / 1M
$12.00
Cached input / 1M
$0.2
Context window
65K
Also billed
- Cache write
- $0.375 / 1M
- Audio input
- $2.00 / 1M
- Image input
- $0.000002 / image
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in — out —
- 90d
- in decreased 0.0% out decreased 0.0%
- 1y
- in decreased 0.0% out decreased 0.0%
- Since launch
- in decreased 0.0% out decreased 0.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 29 Jun 2026 | $2.00 | $12.00 | $0.2 | Imported from OpenRouter | openrouter.ai |
| 18 Jun 2026 | $2.00 | $12.00 | $0.2 | Imported from OpenRouter | openrouter.ai |