Skip to main content
ReachAPIReachAPI
Gemini 3 Pro Image Preview

Gemini 3 Pro Image Preview

Google's highest-quality preview image model for professional asset generation, editing, and grounded visual production.

PreviewProfessional AssetsSearch Grounding

Input Types

Text + image

Professional generation and editing

Context Window

65,536

Output up to 32,768 tokens

Search Grounding

Supported

Grounded image workflows

Resolution Pricing

1K / 2K / 4K

Priced per generated image

输入

$1.8$2.0000

10% off

1M tokens

输出

$108$120.0000

10% off

1M tokens

模型代码gemini-3-pro-image-preview

试玩区

gemini-3-pro-image-preview
参考图片0/14

Click or drag

分辨率 (sent to backend)

Aspect Ratio (sent to backend)

暂无输出

定价

方案上下文窗口最大输出输入输出缓存写入缓存读取
gemini-3-pro-image
--
$1.8$2.000010% off

1M tokens

$108$120.000010% off

1M tokens

--

Pricing follows the existing ReachAPI Gemini image pricing memo used for Nano Banana Pro.

Google's public pricing guide lists Gemini 3 Pro Image Preview with token-based text input pricing and notes that image output pricing varies by resolution.

README

Gemini 3 Pro Image Preview is Google's premium preview image model, designed for studio-grade image generation and editing with stronger reasoning, search grounding, and high-fidelity creative control.
  • Google describes Gemini 3 Pro Image Preview as a sophisticated reasoning-driven engine for professional-grade image editing and generation.
  • The model supports text and image inputs, image and text outputs, structured outputs, thinking, search grounding, and a 65,536 token input limit with up to 32,768 output tokens.
  • On ReachAPI, this raw Google model slug maps to the same premium image workflow also surfaced under the Nano Banana Pro product naming.

API

查看 API 文档以获取请求格式、参数说明和集成方式。

Google's highest-quality preview image model for professional asset generation, editing, and grounded visual production.

模型代码

gemini-3-pro-image-preview

查看 API 文档

API

端点

POST /v1/images/create

认证

Authorization: Bearer YOUR_REACH_API_KEY
Content-Type: application/json

示例

curl -X POST "https://direct.reachapi.ai/v1/images/create" \
  -H "Authorization: Bearer YOUR_REACH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nanobanana-pro",
    "input": {
      "prompt": "A luxury perfume bottle hero image on a marble surface",
      "aspect_ratio": "4:5",
      "resolution": "2k",
      "output_format": "png"
    }
  }'

相关模型

同一厂商的其他模型

Gemini 3.1 Flash Image Preview

Google's high-efficiency preview image model for fast generation, conversational editing, and grounded visual workflows.

Gemini 3.1 Pro Preview

Google's preview model for the most complex reasoning and agentic workflows.

Gemini 2.5 Flash

Google's price-performance Gemini model for balanced, multimodal production workloads.

Gemini 2.5 Flash Image

Google's high-velocity native image model for low-latency generation and conversational editing.

Gemini 2.5 Flash Lite

Google's low-latency Gemini model for cost-sensitive, high-volume workloads.

Gemini 2.5 Pro

Google's most advanced reasoning Gemini model for complex multimodal problem solving.