Nano Banana 2 (Gemini 3.1 Flash Image)
Google· released 18 Jun 2026
google/gemini-3.1-flash-image- Input / 1M tokens
- $0.5
- Output / 1M tokens
- $3
Longest answer: 33K tokens
About
Nano Banana 2, also known as Gemini 3.1 Flash Image, is Google’s image generation and editing model. It accepts text and image inputs and produces images as well as text. The model supports vision and reasoning, with a context window of 131,072 tokens and a maximum output of 32,768 tokens. Google describes its visual quality as Pro-level and its speed as Flash speed. For teams planning usage by token volume, the listed input price is USD 0.5 per 1M tokens and the output price is USD 3 per 1M tokens. Its model ID is google/gemini-3.1-flash-image. The model was released on 2026-06-18, and its official listing is on OpenRouter. Its text-and-image input and image-and-text output make it a candidate for workflows that need image creation or editing alongside text interaction.
Who it is for
Teams that need image generation or editing from text and image inputs may find it relevant. Its listed vision and reasoning support may suit multimodal workflows.
What is good
- Generates and edits images.
- Accepts both image and text inputs.
- Supports vision and reasoning.
- Context window is 131,072 tokens.
What to know first
- Input costs USD 0.5 per 1M tokens.
- Output costs USD 3 per 1M tokens.
Verdict
Nano Banana 2 combines image generation and editing with text and image inputs, plus listed vision and reasoning support. Consider its token-based input and output prices when estimating usage.
Details
- Lab
- Googleopenrouter.ai · 3 Oct 2026
- Context
- 131Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.5 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $3 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 32,768 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- image, textopenrouter.ai · 3 Oct 2026
- Open weights
- Noopenrouter.ai · 3 Oct 2026
More newest models
See the list
Listed on Inferse
- Newest Models in 2026466 listed
- Longest-Context Models in 2026466 listed
- Cheapest Language Models in 2026437 listed
- Reasoning Models in 2026332 listed
- Vision Language Models in 2026295 listed
- Google Models: Pricing per 1M Tokens and Context (2026)43 listed
- Image Generation Models in 20269 listed
Sources
- openrouter.ai/google/gemini-3.1-flash-image· checked 3 Oct 2026