Model · Google · Image-Gen
Nano Banana 2.1
Google's current image generation and editing model in the Gemini API (model ID gemini-nano-banana-2.1). Improves visual quality, prompt adherence, multi-turn character consistency, and text rendering, and replaces gemini-3.1-flash-image.
- Modality
- Image-Gen
- License
- Proprietary (Proprietary)
- Context window
- 131,072 tokens 131k-token input and 32k-token output. Outputs 1K (default), 2K, or 4K images, using 1,120 / 1,680 / 3,780 output tokens each.
- Released
- October 6, 2026
- Last verified
- October 28, 2026
- Runs locally
- No
Strengths
- Better visual quality, prompt adherence, and in-image text rendering than gemini-3.1-flash-image
- Keeps characters consistent across multi-turn edits
- Up to 4K output, plus panoramic aspect ratios (1:4, 4:1, 1:8, 8:1)
- Grounding with Google Web and Image Search; thinking levels minimal / medium (default) / high
- Per-image cost of about $0.034 at 1K, $0.050 at 2K, and $0.113 at 4K
Weaknesses
- Image output bills at $30 per MTok against $1.50 per MTok input and $7.50 per MTok text output
- No caching, function calling, structured outputs, or Flex/Priority inference
- Closed weights
Try it
| Where | Type | Notes |
|---|---|---|
| Google AI Studio | hosted-api | API key required |
| Vertex AI | hosted-api | GCP enterprise |
Official sources
- Model docs docs
- Gemini API pricing docs
Change log
- — Initial entry. GA 2026-10-06 per Google's Gemini API changelog, deprecating gemini-3.1-flash-image (no shutdown date announced). $1.50 input, $7.50 text output, $30 image output per MTok — $0.0336 / $0.0504 / $0.113 per 1K / 2K / 4K image; 131k-token input.
Esc