Claude Haiku 4.5 pricing & specs
Anthropic · released 2025-10-15 · ● verified 2026-10-11
input / 1M$1.00
output / 1M$5.00
context200K
max output64K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Claude Haiku 4.5 |
|---|---|---|---|---|
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | 1.05M | −91.2% |
| Claude Haiku 5.5 | $0.10 | $0.50 | 1M | −90% |
| GPT-6 Luna | $0.10 | $0.50 | 1.05M | −90% |
| GLM-5.3-Flash | $0.15 | $0.50 | 1M | −88.1% |
| GPT-5.6 Luna | $0.20 | $1.20 | 1.05M | −77.5% |
// faq
How much does Claude Haiku 4.5 cost?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens. At 50M input and 10M output tokens per month that is about $100.
What is the context window of Claude Haiku 4.5?
200K tokens, with up to 64K output tokens per request.
Does Claude Haiku 4.5 support prompt caching?
Yes. Cached input tokens cost $0.10 per million and cache writes cost $1.25 per million.
What are cheaper alternatives to Claude Haiku 4.5?
Gemini 2.5 Flash-Lite ($0.10 in / $0.40 out), Claude Haiku 5.5 ($0.10 in / $0.50 out), GPT-6 Luna ($0.10 in / $0.50 out) offer the same input types and capabilities for less.
// spec sheet
- input / 1M
- $1.00
- output / 1M
- $5.00
- cache read / 1M
- $0.10
- cache write / 1M
- $1.25
- blended (3:1)
- $2.00
- context
- 200K
- max output
- 64K
- input types
- text · image · pdf
- reasoning
- yes
- tool calling
- yes
- structured output
- yes
- open weights
- no
- knowledge cutoff
- 2025-02-28
- price source
- Anthropic
- aliases
- claude-haiku-4-5-20251001
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | $9.00 |
| Claude Haiku 5.5 | $0.10 | $0.50 | $10.00 |
| GPT-6 Luna | $0.10 | $0.50 | $10.00 |
| Claude Haiku 4.5 | $1.00 | $5.00 | $100 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.