Claude Haiku 5.5
claude-haiku-5-5
Anthropic · reasoning · api
Intelligence
Context
1M
Max output
128K
Input $/1M
$0.10
Output $/1M
$0.50
Modalities
text · image · document
Released
07 Oct 2026
Intelligence Index via Artificial Analysis · 0–100, higher is better
AI summary
● machine-written
Claude Haiku 5.5: Anthropic's fastest model for latency-sensitive tasks
Claude Haiku 5.5 is Anthropic's most efficient model, designed for high-volume, latency-sensitive applications such as classification, extraction, and routing. It supports text, image, and document inputs with a 1M token context window and 128K token max output. The model is available via API in general availability status.
What's new
- Supports document modality in addition to text and image inputs
- 128K token maximum output window
- Tiered pricing: $0.10/M for prompts up to 100K tokens, $0.50/M for longer prompts
Best for
High-volume classification and extraction tasksLatency-sensitive routing applicationsReal-time processing at scale
Common questions about Claude Haiku →
Source: https://docs.claude.com/en/docs/about-claude/models/overview