Modelsclaude-haiku-5-5

Anthropic: Claude Haiku 5.5

claude-haiku-5-5

Anthropic Claude Haiku 5.5 for fast, high-volume classification, extraction, routing, and subagent tasks.

anthropicclaudehaikumultimodalreasoning

Capabilities & limits

Model type: Vision Language
Input modalities
Output modalities
Context: 1,000,000tokens
Max output: 128,000tokens
Vision / images: Yes
Tools & function calling: Not specified

Updated Oct 7, 2026

Pricing

Pay as you go. Rates depend on the provider route you use; below is reference pricing when available.

Input tokens

Up to 100K
- Uncached input tokens
  $0.1 / per 1M tokens
- Output tokens
  $0.5 / per 1M tokens
- Cache hit tokens
  $0.01 / per 1M tokens
- Cache creation tokens
  Cache creation tokens minus Cache creation (5 min), Cache creation (1 hour), then billed
  $0.125 / per 1M tokens
- Cache creation (5 min)
  $0.125 / per 1M tokens
- Cache creation (1 hour)
  $0.2 / per 1M tokens
100K or more
- Uncached input tokens
  $0.5 / per 1M tokens
- Output tokens
  $2.5 / per 1M tokens
- Cache hit tokens
  $0.05 / per 1M tokens
- Cache creation tokens
  Cache creation tokens minus Cache creation (5 min), Cache creation (1 hour), then billed
  $0.625 / per 1M tokens
- Cache creation (5 min)
  $0.625 / per 1M tokens
- Cache creation (1 hour)
  $1 / per 1M tokens

One scenario is selected per request; prices from different rows are not added together. Within the selected scenario, the listed meter charges are added together. For adjusted meters, the named sub-meters are deducted before applying the rate.