Anthropic logoAnthropicanthropic.com

Proprietary

Claude Haiku 4.5pricing, context window and what it's actually good for

Anthropic's fastest model with near-frontier intelligence. 200k-token context, 64k max output. Reliable knowledge cutoff February 2025; training data cutoff July 2025. Uses the earlier tokenizer, so per-token costs are directly comparable with Claude Sonnet 4.6 and earlier.

Context window
200,000 tokens
Max output
64,000 tokens
Released
15 Oct 2025
Knowledge cutoff
Feb 2025
API identifier
claude-haiku-4-5-20251001

Pricing · per 1M tokens

Input$1.00
Output$5.00
Cached input$0.10

Cached input is 10× cheaper on this model — it pays off when you send the same context again and again.

Checked against Anthropic pricing docs on 7 Aug 2026, 11:51 UTC

Used for

Where Claude Haiku 4.5 shows up in practice

The workflows where we shortlist Claude Haiku 4.5 against the alternatives. Each page says why, at what price, and where a cheaper model does the job instead.

Not sure Claude Haiku 4.5 fits your workload?

We'll size the right model for your use case and give you a real cost estimate. One free call, no slides.

Talk to us