Claude Haiku 4.5 Turbo: pricing, context window and benchmarks
Claude Haiku 4.5 Turbo is a multimodal model from Anthropic. It offers a 200,000-token context window, costs $14.37 per million input tokens and $54.76 per million output tokens, and averages 80.0 across the index's benchmark suite.
Pricing
Claude Haiku 4.5 Turbo costs $14.37 per million input tokens and $54.76 per million output tokens. A blended 3:1 input-to-output mix works out to about $24.47 per million tokens. Cached input is listed at $1.94 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $14.37 | per 1M tokens |
| Output | $54.76 | per 1M tokens |
| Cached input | $1.94 | per 1M tokens |
| Blended 3:1 | $24.47 | estimate per 1M tokens |
| 1M in + 1M out | $69.13 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 80.6 | 161 | 73th | |
| GPQA Diamond | 75.1 | 140 | 77th | |
| SWE-bench Verified | 68.4 | 135 | 78th | |
| HumanEval | 87.0 | 86 | 86th | |
| MATH-500 | 83.7 | 132 | 78th | |
| AIME 2025 | 79.2 | 98 | 84th | |
| LiveCodeBench | 71.7 | 153 | 75th | |
| IFEval | 87.1 | 128 | 79th | |
| TruthfulQA | 81.0 | 155 | 74th | |
| HellaSwag | 88.1 | 136 | 77th | |
| MMMU | 77.7 | 101 | 83th | |
| Arena Elo | 1434.5 | 109 | 82th |
What Claude Haiku 4.5 Turbo is good for
Claude Haiku 4.5 Turbo is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $14.37 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 200,000-token context window for long documents and agent traces.
- Accepts more than text, including image input where the provider supports it.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $14.37 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| GLM-4.6 | Zhipu AI | 128000 | $5.10 | 80.2 |
| DeepSeek-R1 Base | DeepSeek | 400000 | $5.05 | 80.1 |
| Claude Haiku 4.5 Turbo | Anthropic | 200000 | $14.37 | 80.0 |
| ERNIE 4.5 | Baidu | 65536 | $13.44 | 80.0 |
| Command A Max | Cohere | 400000 | $14.28 | 79.9 |
| Reka Core Pro | Reka AI | 65536 | $13.44 | 79.9 |
FAQ
How much does Claude Haiku 4.5 Turbo cost?
Claude Haiku 4.5 Turbo is listed at $14.37 per million input tokens and $54.76 per million output tokens. Cached input is $1.94 per million tokens. A blended 3:1 input-to-output mix is about $24.47 per million tokens.
What is the context window of Claude Haiku 4.5 Turbo?
Claude Haiku 4.5 Turbo has a context window of 200,000 tokens and can emit up to 32,768 output tokens per request in this index.
Is Claude Haiku 4.5 Turbo open weights?
No. Claude Haiku 4.5 Turbo is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Claude Haiku 4.5 Turbo score on benchmarks?
Claude Haiku 4.5 Turbo averages 80.0 across the scored benchmarks in this index, ranking #119 of 600 models. Its strongest relative result is Arena Elo at 1434.5.
What is Claude Haiku 4.5 Turbo best for?
Claude Haiku 4.5 Turbo is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $14.37 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.