Gemini Nano Banana 2.1
gemini-nano-banana-2.1Gemini Nano Banana 2.1 (gemini-nano-banana-2.1) 是最新的高效图片生成和对话式智能修图模型。Nano Banana 2（Gemini 3.1 Flash Image）的更新版本，在保持 Flash 级速度和成本效益的同时，在视觉质量、提示遵循度、多轮对话角色一致性和文本呈现方面实现了显著改进。它是 Gemini 3 Pro Image (Nano Banana Pro) 的更高效版本。
- Starting price
- Input / Output · 1M
- Context
- —
- Maximum input window
- Modalities
- →
Pricing by Supplier
Capabilities / Supported modalities
Provider & data privacy
SentencePiece (Gemini)Performance
Benchmarks
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis 2026-09-30·Gemini Nano Banana 2.1
This model is not included in the current benchmark snapshot.
Missing models or measurements are not zero scores.
Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.
About Gemini Nano Banana 2.1
提升了 1K、2K 和 4K 输出分辨率（默认 1K）下的视觉质量和真实感 修复了在 2K 和 4K 分辨率下，宽屏和全景宽高比（1:4、4:1、1:8、8:1）的平铺伪影 增强了文本渲染和信息图布局准确性 支持多图融合，最多可使用 14 张参考图片（最多可保持 4 个角色的一致性，最多可保持 10 个对象的逼真度） 依托 Google 网页搜索和图片搜索进行接地 可配置的思考等级（minimal、medium [默认] 和 high）
Use cases and prompting
Starting points for evaluation; supported inputs and options are listed in API access.
Use cases to explore
- Explore product visuals, campaign concepts and illustration drafts.
- Compare composition and visual style across several prompt variations.
Practical tips
Specify the subject, composition, lighting and style. Only include reference images or editing parameters when the endpoint supports them.
Example prompt
A minimalist product photograph of a ceramic cup on pale stone, soft window light, ample empty space on the right, warm neutral colors.
API access
API documentation
Code samples
/v1beta/models/gemini-nano-banana-2.1:generateContent| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Replace <YOUR_API_KEY> with the API key from your token settings.
Authentication
All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.
Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.
Supported parameters
| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Rate limits
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| Google AI Studio | Unlimited | Unlimited | Unlimited |
No restriction
Frequently asked questions about gemini-nano-banana-2.1
What is gemini-nano-banana-2.1?
Gemini Nano Banana 2.1 (gemini-nano-banana-2.1) 是最新的高效图片生成和对话式智能修图模型。Nano Banana 2（Gemini 3.1 Flash Image）的更新版本，在保持 Flash 级速度和成本效益的同时，在视觉质量、提示遵循度、多轮对话角色一致性和文本呈现方面实现了显著改进。它是 Gemini 3 Pro Image (Nano Banana Pro) 的更高效版本。
How do I call gemini-nano-banana-2.1?
Create an API key with access to gemini-nano-banana-2.1, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
How is gemini-nano-banana-2.1 priced?
Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.
How should I evaluate gemini-nano-banana-2.1 for my project?
Specify the subject, composition, lighting and style. Only include reference images or editing parameters when the endpoint supports them.