# Nano Banana

> Nano Banana is a proprietary language model from Google DeepMind, released on 26 Aug 2025. It accepts text and images and generates text and images, with a 33K-token context window and up to 33K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.30 per million input tokens and $2.50 per million output tokens (OpenRouter), across 4 providers we track.

Source page: https://www.aimodel.directory/models/gemini-2-5-flash-image
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Google DeepMind
- **Release date:** 26 Aug 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-2.5-flash-image.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-2.5-flash-image.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-2.5-flash-image.toml)
- **Context window:** 33K (32,768 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-2.5-flash-image.toml)
- **Max output:** 33K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-2.5-flash-image.toml)
- **Knowledge cutoff:** Jun 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-2.5-flash-image.toml)
- **Input:** Text and images (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-2.5-flash-image.toml)
- **Output:** Text and images (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-2.5-flash-image.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-2.5-flash-image.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-2.5-flash-image.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Gemini API | $0.30 | $30 | $0.07 | 33K |
| Google Vertex AI | $0.30 | $30 | – | 33K |
| OpenRouter | $0.30 | $2.50 | $0.03 | 33K |
| Vercel AI Gateway | $0.30 | $2.50 | $0.03 | 33K |

## FAQ

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

Nano Banana has a context window of 32,768 tokens (33K) and can generate up to 32,768 tokens in a single response, according to models.dev.

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

Through Gemini API, Nano Banana costs $0.30 per million input tokens and $30 per million output tokens. The lowest listed price is $0.30 input / $2.50 output through OpenRouter. Prices last verified 4 Oct 2026.

### Is Nano Banana open source?

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

### When was Nano Banana released?

Google DeepMind released Nano Banana on 26 Aug 2025, according to models.dev.

### Which providers offer Nano Banana?

We track Nano Banana on 4 providers: Gemini API, Google Vertex AI, OpenRouter, Vercel AI Gateway.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Nano Banana", https://www.aimodel.directory/models/gemini-2-5-flash-image