Back to all models

Claude 3 Haiku

Compact Claude 3 model with vision for fast, affordable inference.

claude-3-haiku
STABLEModel DeactivatedGet StartedView uptime
200,000 context
Starting at $0.24/M (5% off) input tokens
Starting at $1.19/M (5% off) output tokens
Streaming
Vision
Tools

Select Provider

All Providers for Claude 3 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 Jul 14, 2025Deactivated since Oct 14, 2025
Input
$0.25$0.2375
5% off
/M tokens
Cached
$0.03$0.0285
5% off
/M tokens
Output
$1.25$1.1875
5% off
/M tokens
Get Started