Claude Opus 4.5 Mini: pricing, context window and benchmarks
Claude Opus 4.5 Mini is a multimodal model from Anthropic. It offers a 65,536-token context window, costs $12.72 per million input tokens and $48.32 per million output tokens, and averages 79.0 across the index's benchmark suite.
Pricing
Claude Opus 4.5 Mini costs $12.72 per million input tokens and $48.32 per million output tokens. A blended 3:1 input-to-output mix works out to about $21.62 per million tokens. Cached input is listed at $1.32 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $12.72 | per 1M tokens |
| Output | $48.32 | per 1M tokens |
| Cached input | $1.32 | per 1M tokens |
| Blended 3:1 | $21.62 | estimate per 1M tokens |
| 1M in + 1M out | $61.04 | 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 | 83.0 | 103 | 83th | |
| GPQA Diamond | 76.2 | 113 | 81th | |
| SWE-bench Verified | 64.8 | 216 | 64th | |
| HumanEval | 82.8 | 162 | 73th | |
| MATH-500 | 84.2 | 119 | 80th | |
| AIME 2025 | 76.1 | 138 | 77th | |
| LiveCodeBench | 72.5 | 136 | 77th | |
| IFEval | 84.3 | 205 | 66th | |
| TruthfulQA | 81.1 | 153 | 75th | |
| HellaSwag | 87.1 | 170 | 72th | |
| MMMU | 76.5 | 123 | 80th | |
| Arena Elo | 1403.1 | 201 | 67th |
What Claude Opus 4.5 Mini is good for
Claude Opus 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 $12.72 per million input tokens, it sits in the mid-range of the index, and the 65,536-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 $12.72 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 4 Scout Instruct | Meta AI | 32768 | $4.59 | 79.1 |
| Mistral Large 3 Chat | Mistral AI | 1000000 | $4.90 | 79.1 |
| Sonar Pro | Perplexity | 128000 | $13.01 | 79.1 |
| Claude Opus 4.5 Mini | Anthropic | 65536 | $12.72 | 79.0 |
| QwQ Instruct | Alibaba Cloud | 65536 | $4.62 | 79.0 |
| Sonar Pro Turbo | Perplexity | 128000 | $13.55 | 79.0 |
FAQ
How much does Claude Opus 4.5 Mini cost?
Claude Opus 4.5 Mini is listed at $12.72 per million input tokens and $48.32 per million output tokens. Cached input is $1.32 per million tokens. A blended 3:1 input-to-output mix is about $21.62 per million tokens.
What is the context window of Claude Opus 4.5 Mini?
Claude Opus 4.5 Mini has a context window of 65,536 tokens and can emit up to 8,192 output tokens per request in this index.
Is Claude Opus 4.5 Mini open weights?
No. Claude Opus 4.5 Mini is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Claude Opus 4.5 Mini score on benchmarks?
Claude Opus 4.5 Mini averages 79.0 across the scored benchmarks in this index, ranking #149 of 600 models. Its strongest relative result is Arena Elo at 1403.1.
What is Claude Opus 4.5 Mini best for?
Claude Opus 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 $12.72 per million input tokens, it sits in the mid-range of the index, and the 65,536-token context window is enough for large files and multi-file diffs.