Anthropicclaude-3-5-haiku
Claude 3.5 Haiku API Pricing
High-velocity low-latency model. Prompt caching hit receives 90% discount ($0.08/1M); cache write at $1.00/1M. Message Batches API offers 50% off.
Base Input Price$0.80/ 1M tokens
Base Output Price$4.00/ 1M tokens
Prompt Cache Read$0.080-90% discount
Batch API Rate-50%24h async offload
Inference Hosts & Aggregator Providers
Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers