Claude Haiku 4.5 API pricing
As of October 22, 2026, Anthropic Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens on Anthropic's own API, with cached input at $0.10 per million.
Claude Haiku 4.5 benchmarks and specs · Every Anthropic model's price
- Input, per million tokens$1.00
- Output, per million tokens$5.00
- Cached input, per million$0.10
- Context window200K tokens
- Max output64K tokens
- Output speedNot measured
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0035 | $3.50 | Yes |
| Repository review | 50K input + 3K output tokens | $0.065 | $65.00 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.250 | $250.00 | No, it would need splitting |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $0.56 | $560.00 |
Price history
We have read Anthropic's own price every day since October 21, 2026. It has not changed yet; any change will be listed here with its date.
- October 21, 2026 First recorded: $1.00 input, $5.00 output
Cheaper models as good as Claude Haiku 4.5
Models within two points of Claude Haiku 4.5 or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- Qwen3.5-Flash$0.26 Overall 50.1 against 41.0 · 95% cheaper output
- MiMo-V2.6-Flash$0.28 Overall 60.8 against 41.0 · 94% cheaper output
- DeepSeek V4 Flash 0731$0.28 Overall 55.2 against 41.0 · 94% cheaper output
- Qwen3 30B A3B Instruct 2507$0.30 Overall 41.5 against 41.0 · 94% cheaper output
- MiMo-V2.5$0.336 Overall 50.7 against 41.0 · 93% cheaper output
Claude Haiku 4.5 pricing questions
- How much does Claude Haiku 4.5 cost per million tokens?
- $1.00 per million input tokens and $5.00 per million output tokens, as listed on OpenRouter on October 22, 2026.
- Does Claude Haiku 4.5 support prompt caching?
- Yes. OpenRouter lists cached input at $0.10 per million tokens, against $1.00 for uncached input.
- Is there a cheaper model as good as Claude Haiku 4.5?
- Qwen3.5-Flash scores 50.1 on the LLMBenchmark Index, within two points of Claude Haiku 4.5 or above it, and costs $0.26 per million output tokens.
- Has the price of Claude Haiku 4.5 changed?
- Not since we started recording it daily on October 21, 2026.