Gemini 2.5 Flash Image (Nano Banana) | ||
|---|---|---|
Model Provider The organization behind this AI's development | Google | |
Input Context Window Maximum input tokens this model can process at once | 32.8K tokens | 32.8K tokens |
Output Token Limit Maximum output tokens this model can generate at once | Not specified tokens | 32.8K tokens |
Release Date When this model first became publicly available | October 17, 2025 29 days ago October 17th, 2025 | October 7, 2025 1 month ago October 7th, 2025 |
Cogito V2 Preview Llama 405B | Gemini 2.5 Flash Image (Nano Banana) | |
|---|---|---|
Input Types Supported input formats | 📝Text | 🖼️Image📝Text |
Output Types Supported output formats | 📝Text | 🖼️Image📝Text |
Tokenizer Text encoding system | Llama3 | Gemini |
Key Features Advanced capabilities | ✓Function Calling✓Structured Output✓Reasoning ModeContent Moderation | Function Calling✓Structured OutputReasoning ModeContent Moderation |
Open Source Model availability | Available on HuggingFace → | Proprietary |
Gemini 2.5 Flash Image (Nano Banana) | ||
|---|---|---|
Input Token Cost Cost per million input tokens | $3.50 per million tokens | $0.30 per million tokens |
Output Token Cost Cost per million outut tokens | $3.50 per million tokens | $2.50 per million tokens |
Gemini 2.5 Flash Image (Nano Banana) | ||
|---|---|---|
MMLU Measures knowledge across 57 subjects like law, math, history, and science | Benchmark not available. | Benchmark not available. |
MMMU Measures understanding of combined text and images across various domains | Benchmark not available. | Benchmark not available. |
HellaSwag Measures common sense reasoning by having models complete sentences about everyday situations | Benchmark not available. | Benchmark not available. |
Gemini 2.5 Flash Image (Nano Banana) by Google understands both text and images, generates structured data. It can handle standard conversations with its 32.8K token context window. Reasonably priced at $0.30/M input and $2.50/M output tokens. Released October 7th, 2025.