Anthropic: Claude Haiku 4.5 (batch)
Anthropic · Tools · Structured output · Reasoning controls · Sampling controls · Output limits · Released Oct 15, 2025
Provider pricing
Compare provider prices
Published rates for providers serving this model. Open any source to see where and when the price was checked.
| Provider | Input | Output | Cached input | Batch input | Evidence |
|---|---|---|---|---|---|
 OpenRouteropenrouter.ai ↗ | $0.5/ 1M | $2.5/ 1M | $0.05 | $0.5 | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
Performance
Published benchmark results
Benchmark results collected from published sources. Scores from different benchmark versions or test setups may not be directly comparable.
| Benchmark | Category | Score | Origin | Evidence |
|---|---|---|---|---|
| GPQA Diamond | reasoning | 72.90 | Public benchmark | SourceGPQA Diamond via OpenRouter See where this value came from and when it was checked.
|
| TAU-Bench | reasoning | 67.60 | Public benchmark | SourceTAU-Bench via OpenRouter See where this value came from and when it was checked.
|
| Artificial Analysis Intelligence | reasoning | 29.90 | Public benchmark | SourceArtificial Analysis Intelligence via OpenRouter See where this value came from and when it was checked.
|
| Artificial Analysis Coding | reasoning | 43.90 | Public benchmark | SourceArtificial Analysis Coding via OpenRouter See where this value came from and when it was checked.
|
| Artificial Analysis Agentic | reasoning | 16.50 | Public benchmark | SourceArtificial Analysis Agentic via OpenRouter See where this value came from and when it was checked.
|
History
Recent changes
Recorded changes in pricing, availability and other tracked model data.