claude-haiku-5-5
Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It supports adaptive thinking with the effort parameter, a 1M token context window, and up to 128k output tokens.
上下文
1M
输入 / 1M
$0.10
输出 / 1M
$0.50
Modalities
协议
1- messages
可用性与性能
近 7 天
正在加载模型性能
能力
文本视觉长上下文缓存
计费明细
输入 Tokens
$0.1/1M
输出 Tokens
$0.5/1M
缓存命中
$0.01/1M
缓存输入
$0.01/1M
缓存写入(5m)
$0.125/1M
缓存写入(1h)
$0.2/1M
缓存写入
$0.125/1M
音频输入
$0.1/1M
音频输出
$0.5/1M
input_above_threshold
$0.5/1M
cached_input_above_threshold
$0.05/1M
output_above_threshold
$2.50/1M
input_audio_above_threshold
$0.5/1M
缓存写入（长上下文）
$0.625/1M
价格以 USD / 1M tokens 展示（除非另注单位）。Batch API 与缓存命中会享有额外折扣，最终以工作空间实时费率为准。