# Nano Banana 2.1 vs Llama 4 Maverick 17B Instruct - AI Model Comparison

- Page: https://opencode.ai/data/compare/google/gemini-nano-banana-2-1/meta/llama-4-maverick-17b-instruct

|  | Nano Banana 2.1 | Llama 4 Maverick 17B Instruct |
| --- | --- | --- |
| Lab | Google | Meta |
| Context window | 131K | 1M |
| Max output | 33K | 16K |
| Input modalities | text, image, video | text, image |
| Reasoning | Yes | No |
| Tool calling | No | Yes |
| Open weights | No | Yes |
| Release date | 2026-10-06 | 2025-04-05 |
| Input price per 1M tokens | $1.50 | $0.27 |
| Output price per 1M tokens | $7.50 | $0.85 |
| Cached input price per 1M tokens | - | - |
| OpenCode tokens: past 2 months | - | - |
| Share of all tokens | - | - |
| Rank by tokens last week | - | - |
| Unique users | - | - |
| Weekly retention | - | - |

Model pages: [Nano Banana 2.1](https://opencode.ai/data/google/gemini-nano-banana-2-1.md), [Llama 4 Maverick 17B Instruct](https://opencode.ai/data/meta/llama-4-maverick-17b-instruct.md)

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.