Gemini 4 Carbon is Google DeepMind’s multimodal model for complex coding, long-running agent workflows, and cybersecurity defense. Building on Gemini 4 Argon, it improves software engineering, vulnerability detection and remediation, multimodal understanding, and execution across challenging, multi-step tasks.
定价
輸入模式
- Text
- Vision
- Audio
- Video
輸出模式
- Text
上下文
- 1.05M tokens
最大輸出
- 65.5K tokens
能力
- Thinking
- Streaming
- Tool calling
- Web search
- URL context
- Code interpreter
- Computer use
- File search
- Memory tool
- Structured outputs
- Structured decision
- Citations
- Prompt caching
- Background mode
- Server-side sessions
供應商
VertexAI gemini-4-carbon
Pricing$2$10
Cache Read$0.1/M tokens
Input Video$2/M tokens
Input Audio$2/M tokens
Web Search$0.014/request
PrecisionⓘNot Disclosed
Latency75.7S
Throughput25.4TPS
Uptime
0.00% uptime 2 days ago
100.00% uptime yesterday
98.86% uptime today
Google AI Studio gemini-4-carbon
Pricing$2$10
Cache Read$0.1/M tokens
Input Video$2/M tokens
Input Audio$2/M tokens
Web Search$0.014/request
PrecisionⓘNot Disclosed
Latency13.4S
Throughput75.9TPS
Uptime
0.00% uptime 2 days ago
100.00% uptime yesterday
99.93% uptime today
性能对比 gemini-4-carbon
Uptime 指過去 72 小時內請求成功的百分比。AIHubMix 持續監控每個供應商,當某個供應商回傳錯誤或回應過慢時,會自動切換到次佳供應商重試;Latency 指請求的總往返耗時(越低越好);Throughput 指模型的輸出速度(每秒 token 數,越高越好)。
Uptime
Loading...
Latency
Loading...
Throughput
Loading...
快速开始
Python