Claude Haiku 5.5 is Anthropic’s next-generation product, designed for high-throughput, cost-sensitive tasks. It can reliably handle fast and repetitive workloads such as summarization, context compression, database queries, and classification requests. It is also well suited to be used as a sub-agent model in programming workflows alongside Opus 5.5 and Sonnet 5.5.
定价
输入模态
- Text
- Vision
输出模态
- Text
上下文
- 1M tokens
最大输出
- 128K tokens
能力
- Thinking
- Streaming
- Tool calling
- Web search
- URL context
- Code interpreter
- Computer use
- File search
- Memory tool
- Document input
- PDF input
- Structured outputs
- Structured decision
- Citations
- Prompt caching
- Background mode
- Server-side sessions
提供商
AWS claude-haiku-5-5
Tier输入<=100K
Pricing$0.1$0.5
Cache Read$0.01/M tokens
Web Search$0.01/request
Cache Write$0.125/M tokens
Cache Write 5 Minutes$0.125/M tokens
Cache Write 1 Hour$0.2/M tokens
Tier100K<输入
Pricing$0.5$2.5
Cache Read$0.05/M tokens
Web Search$0.01/request
Cache Write$0.625/M tokens
Cache Write 5 Minutes$0.625/M tokens
Cache Write 1 Hour$1/M tokens
PrecisionⓘNot Disclosed
Latency4.1S
Throughput129.7TPS
Uptime
99.96% uptime 2 days ago
100.00% uptime yesterday
99.97% uptime today
VertexAI claude-haiku-5-5
Tier输入<=100K
Pricing$0.1$0.5
Cache Read$0.01/M tokens
Web Search$0.01/request
Cache Write$0.125/M tokens
Cache Write 5 Minutes$0.125/M tokens
Cache Write 1 Hour$0.2/M tokens
Tier100K<输入
Pricing$0.5$2.5
Cache Read$0.05/M tokens
Web Search$0.01/request
Cache Write$0.625/M tokens
Cache Write 5 Minutes$0.625/M tokens
Cache Write 1 Hour$1/M tokens
PrecisionⓘNot Disclosed
Latency0.6S
Throughput187.4TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today
性能对比 claude-haiku-5-5
Uptime 指过去 72 小时内请求成功的百分比。AIHubMix 持续监控每个供应商,当某个供应商返回错误或响应过慢时,会自动切换到次优供应商重试;Latency 指请求的总往返耗时(越低越好);Throughput 指模型的输出速度(每秒 token 数,越高越好)。
Uptime
Loading...
Latency
Loading...
Throughput
Loading...
快速开始
Python