Claude 4.5Released 2025-10-01
Claude Haiku 4.5
Fast and affordable for high-volume tasks
Family
Claude 4.5
Release Date
2025-10-01
Best For
Classification, extraction, quick Q&A, high-volume processing
Overview
Claude Haiku 4.5 is the fast, affordable model in the Claude 4.5 family. At just $1/M input and $5/M output tokens, it's ideal for high-volume tasks that don't require deep reasoning. It maintains the full 200K context window while delivering rapid responses at minimal cost. The best choice for latency-sensitive applications at scale.
Pricing
Input / 1M tokens
$1.00
Output / 1M tokens
$5.00
Context Window
200K
Max Output
8K
API model ID:
claude-haiku-4-5-20251001Key Features
✓Low cost: $1/M input, $5/M output
✓Fast response times for high-throughput applications
✓Full 200K token context window
✓Strong at classification and extraction tasks
✓Suitable for real-time and latency-sensitive applications
Use Cases
Text classification and categorization
Named entity recognition and extraction
Quick Q&A and FAQ responses
Content moderation at scale
High-volume batch processing
Form auto-completion and data entry
Benchmarks
| Benchmark | Score |
|---|---|
| MMLU (5-shot) | 78.2% |
| Coding (HumanEval) | 90.2% |