Gemini Nano Banana 2.1
Gemini Nano Banana 2.1 is Google's generally available image model, released October 6, 2026 on the Gemini API as gemini-nano-banana-2.1.
Provider
Model family
Google Gemini
Image generation model
Cost tier
Nano Banana
Status
Current
Release Oct 6, 2026
Why teams choose it
Long-context and Gemini surfaces
Helps when you consolidate analysis in Google-hosted AI paths and rely on large-context ingestion or multimodal prompts.
Long-context analysis
Helps teams summarize, compare, and extract insights from long documents without losing important nuance.
Document-heavy workflows
Useful where teams ingest PDFs, slides, audio, or long threads and need repeatable extraction—not one-off prompting.
Cost-efficient routing
Useful as part of a routing stack where cheap models handle drafts and confirmations and this tier handles genuinely hard passages.
Tradeoffs to know
- No separate dollar rate for gemini-nano-banana-2.1 on the Gemini pricing page as of October 7, 2026.
- Context caching, function calling, structured outputs, Live API, code execution, and file search are not supported.
- Nano Banana 2 (gemini-3.1-flash-image) shuts down October 29, 2026.
Technical specs
- Inputs
- text, image, video, pdf
- Outputs
- image, text
- Capabilities
- Text, image, video, and PDF inputs, 1K, 2K, and 4K image output, including panoramic ratios, Up to 14 reference images, Thinking levels minimal, medium, and high, Google Search grounding and Batch API
- License
- Proprietary API
- API ID
gemini-nano-banana-2.1- Resolutions
- 1K, 2K, 4K
- Thinking Levels
- minimal, medium, high
- Reference Images
- 14
- Predecessor Api Id
- gemini-3.1-flash-image
- Predecessor Shutdown
- 2026-10-29
- Default Thinking Level
- medium
Benchmarks
No independent or vendor benchmark scores in this catalog entry.
Google Gemini family lineup
Current models
Related models
Gemini Nano Banana 2.1 FAQ
What is Gemini Nano Banana 2.1?
1. 1-flash-image), which the changelog deprecates with a shutdown on October 29, 2026. The model page lists a 131,072-token input limit and a 32,768-token output limit, with text, image, video, and PDF inputs and image plus text outputs. Resolutions are 1K by default, plus 2K and 4K, including wide ratios 1:4, 4:1, 1:8, and 8:1. It accepts up to 14 reference images, with up to 4 characters and up to 10 objects, and thinking levels minimal, medium (the default), and high. Google Search grounding and the Batch API are supported. 1.
When does Gemini Nano Banana 2.1 fit best?
High-resolution image generation and editing from text or reference images
What should teams watch out for with Gemini Nano Banana 2.1?
No separate dollar rate for gemini-nano-banana-2.1 on the Gemini pricing page as of October 7, 2026.
Explore next
Models, tools, and comparisons that connect to this reference.