# Nano Banana 2 Lite

> Nano Banana 2 Lite is a proprietary language model from Google DeepMind, released on 30 Jun 2026. It accepts text and images and generates text and images, with a 66K-token context window and up to 4K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.25 per million input tokens and $1.50 per million output tokens (OpenRouter), across 3 providers we track.

Source page: https://www.aimodel.directory/models/gemini-3-1-flash-lite-image
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Google DeepMind
- **Release date:** 30 Jun 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.1-flash-lite-image.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.1-flash-lite-image.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.1-flash-lite-image.toml)
- **Context window:** 66K (65,536 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.1-flash-lite-image.toml)
- **Max output:** 4K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.1-flash-lite-image.toml)
- **Knowledge cutoff:** Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.1-flash-lite-image.toml)
- **Input:** Text and images (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.1-flash-lite-image.toml)
- **Output:** Text and images (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.1-flash-lite-image.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.1-flash-lite-image.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.1-flash-lite-image.toml)
- **Structured output:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-3.1-flash-lite-image.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Gemini API | $0.25 | $30 | – | 66K |
| OpenRouter | $0.25 | $1.50 | – | 66K |
| Vercel AI Gateway | $0.25 | $1.50 | $0.03 | 66K |

## FAQ

### What is the context window of Nano Banana 2 Lite?

Nano Banana 2 Lite has a context window of 65,536 tokens (66K) and can generate up to 4,096 tokens in a single response, according to models.dev.

### How much does the Nano Banana 2 Lite API cost?

Through Gemini API, Nano Banana 2 Lite costs $0.25 per million input tokens and $30 per million output tokens. The lowest listed price is $0.25 input / $1.50 output through OpenRouter. Prices last verified 4 Oct 2026.

### Is Nano Banana 2 Lite open source?

No. Nano Banana 2 Lite is a proprietary model; Google DeepMind has not released its weights. It is available through APIs including Gemini API, OpenRouter, Vercel AI Gateway.

### When was Nano Banana 2 Lite released?

Google DeepMind released Nano Banana 2 Lite on 30 Jun 2026, according to models.dev.

### Which providers offer Nano Banana 2 Lite?

We track Nano Banana 2 Lite on 3 providers: Gemini API, OpenRouter, Vercel AI Gateway.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Nano Banana 2 Lite", https://www.aimodel.directory/models/gemini-3-1-flash-lite-image