Claude Sonnet 4.5 Nano: pricing, context window and benchmarks
Claude Sonnet 4.5 Nano is a mid-range model from Anthropic. It offers a 8,192-token context window, costs $8.93 per million input tokens and $36.88 per million output tokens, and averages 72.0 across the index's benchmark suite.
Pricing
Claude Sonnet 4.5 Nano costs $8.93 per million input tokens and $36.88 per million output tokens. A blended 3:1 input-to-output mix works out to about $15.92 per million tokens. Cached input is listed at $1.05 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $8.93 | per 1M tokens |
| Output | $36.88 | per 1M tokens |
| Cached input | $1.05 | per 1M tokens |
| Blended 3:1 | $15.92 | estimate per 1M tokens |
| 1M in + 1M out | $45.81 | 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 | 77.3 | 268 | 55th | |
| GPQA Diamond | 68.9 | 298 | 50th | |
| SWE-bench Verified | 61.2 | 295 | 51th | |
| HumanEval | 74.8 | 345 | 43th | |
| MATH-500 | 73.1 | 355 | 41th | |
| AIME 2025 | 64.2 | 353 | 41th | |
| LiveCodeBench | 61.2 | 359 | 40th | |
| IFEval | 82.2 | 269 | 55th | |
| TruthfulQA | 75.6 | 317 | 47th | |
| HellaSwag | 83.0 | 319 | 47th | |
| MMMU | 70.1 | 297 | 51th | |
| Arena Elo | 1364.3 | 334 | 44th |
What Claude Sonnet 4.5 Nano is good for
Claude Sonnet 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 $8.93 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.
- Premium input pricing at $8.93 per million tokens.
- 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 |
|---|---|---|---|---|
| Llama 3.1 Base | Meta AI | 32768 | $3.39 | 72.2 |
| Llama 3 Replicate Base | Replicate | 65536 | $3.15 | 72.1 |
| Claude Sonnet 4.5 Nano | Anthropic | 8192 | $8.93 | 72.0 |
| Mixtral Groq Chat | Groq | 8192 | $3.09 | 72.0 |
| o4 Nano | OpenAI | 65536 | $8.61 | 72.0 |
| Mixtral Turbo Instruct | Together AI | 32768 | $3.16 | 71.9 |
FAQ
How much does Claude Sonnet 4.5 Nano cost?
Claude Sonnet 4.5 Nano is listed at $8.93 per million input tokens and $36.88 per million output tokens. Cached input is $1.05 per million tokens. A blended 3:1 input-to-output mix is about $15.92 per million tokens.
What is the context window of Claude Sonnet 4.5 Nano?
Claude Sonnet 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 Sonnet 4.5 Nano open weights?
No. Claude Sonnet 4.5 Nano is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Claude Sonnet 4.5 Nano score on benchmarks?
Claude Sonnet 4.5 Nano averages 72.0 across the scored benchmarks in this index, ranking #327 of 600 models. Its strongest relative result is Arena Elo at 1364.3.
What is Claude Sonnet 4.5 Nano best for?
Claude Sonnet 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 $8.93 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.