Anthropic · released 2025-10
Claude Haiku 4.5
Fast, cheap, surprisingly smart.
context
200K
output max
8K
input /M
$1.00
output /M
$5.00
cached in /M
$0.10
modalities
T·I
Verdict
What it's actually good at
Strengths
- +Very fast
- +Great cost profile
- +Strong at structured output
Weaknesses
- −Weaker on deep reasoning
- −Smaller context than siblings
Our scores
reasoning
7.0
coding
7.0
writing
8.0
speed
10.0
value
10.0
Smallest Claude with outsized capabilities. Use for classification, routing, and high-throughput workloads.
Pricing
Cost at common volumes
| Monthly volume | Input | Output | Est. monthly |
|---|---|---|---|
| Side project | 1M tok | 0.3M tok | $2.50 |
| Growing app | 50M tok | 15M tok | $125.00 |
| Production | 500M tok | 150M tok | $1250.00 |
| Scale | 5000M tok | 1500M tok | $12500.00 |
Estimates assume uncached input. Prompt caching and batch APIs can cut this by 50–90% for many workloads. Use the calculator →
Head-to-head