Back to all models

Claude Haiku 4.5

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

claude-haiku-4-5
STABLEGet StartedView uptime
200,000 context
Starting at $0.70/M (30% off) input tokens
Starting at $3.50/M (30% off) output tokens
Streaming
Tools
JSON Output

Select Provider

All Providers for Claude Haiku 4.5

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

Anthropic
Context: 200k
Input
$1
/M tokens
Cached
$0.1
/M tokens
Output
$5
/M tokens
+ $0.010 per search
Get Started
AWS Bedrock
Context: 200k30% off
Input
$1$0.7
/M tokens
Cached
$0.1$0.07
/M tokens
Output
$5$3.5
/M tokens
Get Started