Claude Haiku 4.5 API pricing
Anthropic's smallest and fastest current model, Claude Haiku 4.5, at $1 / $5 per 1M tokens with a 200K context window.
Claude Haiku 4.5 prices
What it costs in practice
Claude Haiku 4.5 at list prices, no batch discount.
| 1,000 chat replies1,500 tokens in and 300 out each | $3.00 |
|---|---|
| Summarising 100 long reports20,000 tokens in and 800 out each | $2.40 |
| A month of a coding agent400 tasks, 85% of input cached | $216 |
The coding-agent example assumes 85% of input is served from cache, typical for agents that resend the same context each step. Model your own workload
Details
claude-haiku-4-5Checked 27 Sep 2026 against Anthropic pricing .
Compare Claude Haiku 4.5
Price history
All changesNo price changes recorded since we began tracking in June 2026.
Anthropic pricing rules
- Batch requests cost 50% less.
- Cache reads are billed at a per-model rate, usually a tenth of the input price or less. Cache writes cost 1.25× input for the 5-minute cache and 2× for the 1-hour cache.
- The full 1M-token context window is billed at standard rates on current models.
Questions
How much does Claude Haiku 4.5 cost?
As of 27 Sep 2026, Claude Haiku 4.5 costs $1 per million input tokens and $5 per million output tokens, and $0.10 per million cached input tokens. Batch requests cost 50% less. Prices checked 27 Sep 2026.
What is Claude Haiku 4.5's context window?
200K tokens, with up to 64K tokens of output.
Does Claude Haiku 4.5 support prompt caching?
Yes. Repeated input read from the cache costs $0.10 per million tokens, 90% less than normal input.