Gemini Robotics-ER 2 Preview
面向机器人的视觉语言模型，支持空间推理、视频理解和多步工具编排。
规格
- 上下文
- 131.1K
- 最大输出
- 65.5K
- 输入价
- $1/ 百万 Token
- 输出价
- $5/ 百万 Token
- 发布日期
- 2026-07-30
上下文
- 上下文
- 131.1K
- 最大输入
- 131.1K
- 最大输出
- 65.5K
价格 · USD / 百万 Token
- 输入
- $1
- 输出
- $5
- 缓存读取
- $0.1
- 缓存写入
- —
输入输出
- 输入
- 文本图像视频音频
- 输出
- 文本
API
- 接口类型
思考
- 支持思考
- 支持
- 思考等级
- —
源信息
- 状态
- 预览
- 发布日期
- 2026-07-30
- 知识截止
- —
能力
- 已确认
调用方式
1 个 Provider
googlemodel = gemini-robotics-er-2-previewreasoning = generationConfig.thinkingConfig.thinkingLevel
generate
POSThttps://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent
batch
POSThttps://generativelanguage.googleapis.com/v1beta/models/{model}:batchGenerateContent
JSON
标准格式
{
"id": "gemini-robotics-er-2-preview",
"object": "model",
"created": 1785369600,
"owned_by": "google",
"name": "Gemini Robotics-ER 2 Preview",
"api": {
"types": [
"generate",
"batch"
]
},
"limits": {
"context": 131072,
"input": 131072,
"output": 65536
},
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"reasoning": {
"supported": true,
"efforts": []
},
"pricing": {
"currency": "USD",
"unit": "1M_tokens",
"input": 1,
"output": 5,
"cache_read": 0.1,
"cache_write": null
},
"features": [
"tools",
"structured_output",
"streaming",
"caching",
"batch"
],
"info": {
"status": "preview",
"release_date": "2026-07-30",
"knowledge_cutoff": null,
"description": "Vision-language model for robotics with spatial reasoning, video understanding and multi-step tool orchestration.",
"docs": "https://ai.google.dev/gemini-api/docs/models/gemini-robotics-er-2-preview",
"verified_at": "2026-10-11"
}
}官方来源
6
Gemini Robotics-ER 2 Preview | Gemini APIai.google.dev2026-10-10Models | Gemini APIai.google.dev2026-10-10Pricing | Gemini APIai.google.dev2026-10-10Deprecations | Gemini APIai.google.dev2026-10-10Generating content | Gemini APIai.google.dev2026-10-10Release notes | Gemini APIai.google.dev2026-10-11