Claude Sonnet 4.5 Mini: pricing, context window and benchmarks
Claude Sonnet 4.5 Mini is a multimodal model from Anthropic. It offers a 32,768-token context window, costs $11.43 per million input tokens and $50.28 per million output tokens, and averages 76.5 across the index's benchmark suite.
Pricing
Claude Sonnet 4.5 Mini costs $11.43 per million input tokens and $50.28 per million output tokens. A blended 3:1 input-to-output mix works out to about $21.14 per million tokens. Cached input is listed at $1.56 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $11.43 | per 1M tokens |
| Output | $50.28 | per 1M tokens |
| Cached input | $1.56 | per 1M tokens |
| Blended 3:1 | $21.14 | estimate per 1M tokens |
| 1M in + 1M out | $61.71 | 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 | 267 | 56th | |
| GPQA Diamond | 69.5 | 278 | 54th | |
| SWE-bench Verified | 68.1 | 144 | 76th | |
| HumanEval | 80.9 | 215 | 64th | |
| MATH-500 | 78.6 | 246 | 59th | |
| AIME 2025 | 69.1 | 277 | 54th | |
| LiveCodeBench | 72.8 | 132 | 78th | |
| IFEval | 85.8 | 162 | 73th | |
| TruthfulQA | 81.1 | 154 | 74th | |
| HellaSwag | 86.4 | 197 | 67th | |
| MMMU | 71.8 | 248 | 59th | |
| Arena Elo | 1403.3 | 199 | 67th |
What Claude Sonnet 4.5 Mini is good for
Claude Sonnet 4.5 Mini 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 $11.43 per million input tokens, it sits in the mid-range of the index, and the 32,768-token context window is enough for large files and multi-file diffs.
Strengths
- 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 $11.43 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 3.3 Instruct | Meta AI | 128000 | $4.33 | 76.6 |
| Nemotron 4 | NVIDIA | 65536 | $4.18 | 76.6 |
| Qwen3-Coder Base | Alibaba Cloud | 200000 | $3.99 | 76.6 |
| Claude Sonnet 4.5 Mini | Anthropic | 32768 | $11.43 | 76.5 |
| Qwen3-Max Mini | Alibaba Cloud | 128000 | $11.13 | 76.5 |
| Yi-Lightning Instruct | 01.AI | 128000 | $4.16 | 76.5 |
FAQ
How much does Claude Sonnet 4.5 Mini cost?
Claude Sonnet 4.5 Mini is listed at $11.43 per million input tokens and $50.28 per million output tokens. Cached input is $1.56 per million tokens. A blended 3:1 input-to-output mix is about $21.14 per million tokens.
What is the context window of Claude Sonnet 4.5 Mini?
Claude Sonnet 4.5 Mini has a context window of 32,768 tokens and can emit up to 16,384 output tokens per request in this index.
Is Claude Sonnet 4.5 Mini open weights?
No. Claude Sonnet 4.5 Mini is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Claude Sonnet 4.5 Mini score on benchmarks?
Claude Sonnet 4.5 Mini averages 76.5 across the scored benchmarks in this index, ranking #206 of 600 models. Its strongest relative result is Arena Elo at 1403.3.
What is Claude Sonnet 4.5 Mini best for?
Claude Sonnet 4.5 Mini 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 $11.43 per million input tokens, it sits in the mid-range of the index, and the 32,768-token context window is enough for large files and multi-file diffs.