Claude Haiku 4.5 Nano: pricing, context window and benchmarks
Claude Haiku 4.5 Nano is a mid-range model from Anthropic. It offers a 8,192-token context window, costs $6.47 per million input tokens and $27.98 per million output tokens, and averages 68.7 across the index's benchmark suite.
Pricing
Claude Haiku 4.5 Nano costs $6.47 per million input tokens and $27.98 per million output tokens. A blended 3:1 input-to-output mix works out to about $11.85 per million tokens. Cached input is listed at $0.92 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $6.47 | per 1M tokens |
| Output | $27.98 | per 1M tokens |
| Cached input | $0.92 | per 1M tokens |
| Blended 3:1 | $11.85 | estimate per 1M tokens |
| 1M in + 1M out | $34.45 | 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 | 73.9 | 355 | 41th | |
| GPQA Diamond | 64.5 | 369 | 39th | |
| SWE-bench Verified | 56.9 | 367 | 39th | |
| HumanEval | 71.0 | 388 | 35th | |
| MATH-500 | 71.8 | 369 | 39th | |
| AIME 2025 | 63.5 | 361 | 40th | |
| LiveCodeBench | 59.8 | 369 | 39th | |
| IFEval | 78.2 | 363 | 40th | |
| TruthfulQA | 71.6 | 385 | 36th | |
| HellaSwag | 80.5 | 378 | 37th | |
| MMMU | 64.3 | 386 | 36th | |
| Arena Elo | 1332.1 | 385 | 36th |
What Claude Haiku 4.5 Nano is good for
Claude Haiku 4.5 Nano is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $6.47 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.
Strengths
- Accepts more than text, including image input where the provider supports it.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Context window of 8,192 tokens is small for long-document work.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Claude 3.7 Sonnet Nano | Anthropic | 65536 | $6.93 | 68.9 |
| Arctic | Snowflake | 8192 | $2.72 | 68.8 |
| ERNIE 4.0 Mini | Baidu | 32768 | $7.11 | 68.8 |
| Claude Haiku 4.5 Nano | Anthropic | 8192 | $6.47 | 68.7 |
| Firesearch | Fireworks AI | 32768 | $7.03 | 68.5 |
| Molmo | Allen Institute for AI | 32768 | $2.49 | 68.5 |
FAQ
How much does Claude Haiku 4.5 Nano cost?
Claude Haiku 4.5 Nano is listed at $6.47 per million input tokens and $27.98 per million output tokens. Cached input is $0.92 per million tokens. A blended 3:1 input-to-output mix is about $11.85 per million tokens.
What is the context window of Claude Haiku 4.5 Nano?
Claude Haiku 4.5 Nano has a context window of 8,192 tokens and can emit up to 8,192 output tokens per request in this index.
Is Claude Haiku 4.5 Nano open weights?
No. Claude Haiku 4.5 Nano is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Claude Haiku 4.5 Nano score on benchmarks?
Claude Haiku 4.5 Nano averages 68.7 across the scored benchmarks in this index, ranking #377 of 600 models. Its strongest relative result is Arena Elo at 1332.1.
What is Claude Haiku 4.5 Nano best for?
Claude Haiku 4.5 Nano is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $6.47 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.