Claude Haiku 4.5 (2025-10-01)

Fast, efficient model for high-volume, low-latency applications.

claude-haiku-4-5-20251001
STABLEGet StartedView uptime
200,000 context
Starting at $0.80/M (20% off) input tokens
Starting at $4.00/M (20% off) output tokens
Streaming
Tools
JSON Output

All Providers for Claude Haiku 4.5 (2025-10-01)

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Anthropic
Context: 200k5% off
Input
$1$0.95
/M tokens
Cached
$0.1$0.095
/M tokens
Output
$5$4.75
/M tokens
+ $0.010 per search
Get Started
AWS Bedrock
Context: 200k20% off
Input
$1$0.8
/M tokens
Cached
$0.1$0.08
/M tokens
Output
$5$4
/M tokens
Get Started