Back to all models

Claude 3.5 Haiku

Fastest Claude model for instant responses at scale.

claude-3-5-haiku
STABLEModel DeactivatedGet StartedView uptime
200,000 context
Starting at $0.64/M (20% off) input tokens
Starting at $3.20/M (20% off) output tokens
Streaming
Tools

Select Provider

All Providers for Claude 3.5 Haiku

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

Anthropic
Context: 200k5% off
Deprecated since Dec 19, 2025Deactivated since Feb 19, 2026
Input
$0.8$0.76
5% off
/M tokens
Cached
$0.08$0.076
5% off
/M tokens
Output
$4$3.8
5% off
/M tokens
+ $0.010$0.009 per search
Get Started
AWS Bedrock
Context: 200k20% off
Deprecated since Oct 28, 2025Deactivated since Apr 28, 2026
Input
$0.8$0.64
20% off
/M tokens
Cached
$0.08$0.064
20% off
/M tokens
Output
$4$3.2
20% off
/M tokens
Get Started