Google 推出的 Gemini 2.5 Computer Use 是一款专为长周期自主智能体 (Agent)、工具调用与自动化工作流打造的大模型，具备 128K 上下文窗口、85 Token/秒生成速度与 65/100 综合智能指数（每百万 Token $1.5 输入 / $8 输出）。
Technical Specifications
- Provider
- Category
- flagship
- Release Date
- 2025-10
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- $20 / month
- Reasoning Effort Control
- Configurable (Low / Med / High)
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- models/gemini-2-5-computer-use
- Supported SDK & API Protocol
- Google Gemini API (generateContent) + OpenAI-Compatible SDK
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2027+)
- Production Rate Limits (RPM & TPM)
- 10,000 – 30,000 RPM (Tier 5 Enterprise) · 800,000 – 2,000,000 TPM
- Long-Context Pricing Tier (>128K / >200K)
- Flat rate ($1.5/1M in) across full 128K window
- Prompt Cache Write & TTL Policy
- Implicit + Explicit Context Caching at $0.375/1M with configurable TTL
- Computer Use & Browser GUI Agent
- Supported (Screen coordinate grounding, browser & desktop GUI action loops)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Built-in Google Search Grounding + Managed Python Code Execution Sandbox
- Fine-Tuning & Distillation Support
- Vertex AI Supervised Adapter Tuning & Context Distillation
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile)
- Weights Precision & Quantization
- Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster)
- Minimum GPU VRAM Requirement
- Zero Local VRAM Required (100% Serverless Cloud API)
- Supported Inference Engines
- Managed Google Cloud API
- System Card & Safety Framework
- Google DeepMind Frontier Safety Framework Verified
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier
Gemini 2.5 Computer Use Cost, Context, Hardware & API Integration
For single-user chat, a $20/mo subscription caps your bill below this API volume.
Break-even point: ~57 requests/day equals $20/month.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Gemini 2.5 Computer Use:
Benchmark Scores & 6-Axis Capability Radar
- Terminal-Bench
- 45.2%
- Chatbot Arena Elo
- 1365pts
Strengths
- 提供 128K 上下文窗口与最高 16K 输出容量，核心基准表现优异（Arena Elo 1365）
- 高达 85 Token/秒的生成吞吐量，首字延迟 (TTFT) 仅约 650 毫秒
- 极具竞争力的 API 定价（每百万 Token $1.5 输入 / $8 输出），原生支持提示词缓存、函数调用与结构化 JSON 输出
Limitations & Trade-offs
- 闭源专有云端模型，不支持下载权重进行离线本地物理隔离部署
- 在超长链路的前沿科研推导任务上，深度略逊于顶配重型旗舰推理模型
Editorial Assessment
Gemini 2.5 Computer Use 凭借 65/100 的智能得分、128K 上下文容量与 85 Token/秒的响应速度，在 Google 模型矩阵中提供了极佳的性能与成本平衡。
Best for: 专为长周期自主智能体 (Agent)、工具调用与自动化工作流打造的任务、企业级 RAG 检索增强生成、自动化智能体工作流与高可靠 API 集成。
Compare Gemini 2.5 Computer Use
Frequently Asked Questions about Gemini 2.5 Computer Use
How much does the Gemini 2.5 Computer Use API cost per 1M tokens?+
Gemini 2.5 Computer Use by Google is priced at $1.5 per 1M input tokens and $8 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.375 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the Gemini 2.5 Computer Use pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Gemini 2.5 Computer Use's context window?+
Gemini 2.5 Computer Use features a 128K tokens context window, which equals approximately 96,000 English words or ~256 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 16,384 tokens.
Can I run Gemini 2.5 Computer Use locally on my own GPU (Open Weights)?+
No, Gemini 2.5 Computer Use is a proprietary closed-weights model hosted by Google. It cannot be downloaded for local GPU execution and must be accessed via Google's official API or cloud platform.
Does Google train on data sent to the Gemini 2.5 Computer Use API, and is commercial use allowed?+
API payloads are excluded from model training by default. License tier: Proprietary Commercial API (Google Terms). Full commercial ownership of generated outputs. Supported deployment channels include: Google AI Studio API, Google Cloud Vertex AI.
How does Gemini 2.5 Computer Use perform on coding and reasoning benchmarks?+
Gemini 2.5 Computer Use achieves a composite Intelligence Index of 65/100, scoring N/A% on SWE-bench Verified, N/A% on GPQA Diamond, N/A% on MMLU-Pro, and 1365 pts on Chatbot Arena Elo.
What is Gemini 2.5 Computer Use best used for?+
Gemini 2.5 Computer Use is best suited for: 专为长周期自主智能体 (Agent)、工具调用与自动化工作流打造的任务、企业级 RAG 检索增强生成、自动化智能体工作流与高可靠 API 集成。. Assessment: Gemini 2.5 Computer Use 凭借 65/100 的智能得分、128K 上下文容量与 85 Token/秒的响应速度，在 Google 模型矩阵中提供了极佳的性能与成本平衡。
Google Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Google's flagship reasoning tier:
Gemini 4 Argon
Gemini 3.8 Flash
Gemini 3.7 Flash
Gemini 3.6 Flash
Gemini 3.5 Flash-Lite
Gemini Omni Flash
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Gemini 2.5 Computer Use:
The basic unit of text that a language model processes, typically representing about 3 to 4 English characters or roughly 0.75 words. For example, the sentence "Artificial intelligence is fast" breaks down into about 5 tokens.
A standardized evaluation suite used to objectively measure and rank an AI model's capabilities across specific tasks — such as SWE-bench Verified for software engineering, AIME for competitive math, or MMLU for general knowledge.
The maximum number of tokens a model can consider at once — both the input it reads and the output it writes. A 1,000,000-token context window can hold roughly 750,000 English words in a single request.
An AI model trained via reinforcement learning to spend dynamic compute thinking through complex logic, math, and architectural problems before outputting a solution. Examples include OpenAI o1, o3, and DeepSeek R1.
A step-by-step reasoning technique where an AI model generates intermediate problem-solving thoughts before arriving at a final answer. Native reasoning models like OpenAI o3 and DeepSeek R1 use CoT to solve complex math and coding challenges.
The ability of a language model to recognize when an external capability is needed and output structured JSON arguments to invoke external APIs, databases, or terminal commands. The runtime executes the tool and passes results back to the model.
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.