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.
Context
1M
Input / 1M
$0.10
Output / 1M
$0.50
Modalities
Protocol
1- messages
Status & performance
Last 7 days
Loading model performance
Capabilities
TextVisionLong contextCache
Pricing
Input tokens
$0.1/1M
Output tokens
$0.5/1M
Cache read
$0.01/1M
Cached input
$0.01/1M
Cache write (5m)
$0.125/1M
Cache write (1h)
$0.2/1M
Cache write
$0.125/1M
Audio input
$0.1/1M
Audio output
$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
Cache write (long context)
$0.625/1M
Prices in USD per 1M tokens unless noted otherwise. Batch calls and cache hits receive additional discounts; live rates apply in the Workspace.