Command A Mini: pricing, context window and benchmarks
Command A Mini is a mid-range model from Cohere. It offers a 8,192-token context window, costs $8.12 per million input tokens and $31.21 per million output tokens, and averages 71.0 across the index's benchmark suite.
Pricing
Command A Mini costs $8.12 per million input tokens and $31.21 per million output tokens. A blended 3:1 input-to-output mix works out to about $13.89 per million tokens. Cached input is listed at $0.70 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $8.12 | per 1M tokens |
| Output | $31.21 | per 1M tokens |
| Cached input | $0.70 | per 1M tokens |
| Blended 3:1 | $13.89 | estimate per 1M tokens |
| 1M in + 1M out | $39.33 | 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 | 74.0 | 351 | 42th | |
| GPQA Diamond | 66.8 | 333 | 45th | |
| SWE-bench Verified | 56.5 | 373 | 38th | |
| HumanEval | 76.4 | 321 | 47th | |
| MATH-500 | 75.3 | 317 | 47th | |
| AIME 2025 | 66.6 | 322 | 46th | |
| LiveCodeBench | 60.1 | 367 | 39th | |
| IFEval | 79.2 | 348 | 42th | |
| TruthfulQA | 73.7 | 361 | 40th | |
| HellaSwag | 82.0 | 345 | 43th | |
| MMMU | 70.4 | 282 | 53th | |
| Arena Elo | 1369.4 | 319 | 47th |
What Command A Mini is good for
Command A Mini 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 $8.12 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 $8.12 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 |
|---|---|---|---|---|
| Fusion | OpenRouter | 16384 | $8.41 | 71.1 |
| Gemma 3 Base | Google DeepMind | 65536 | $3.09 | 71.1 |
| Mixtral Base | Mistral AI | 65536 | $2.95 | 71.1 |
| Command A Mini | Cohere | 8192 | $8.12 | 71.0 |
| ERNIE 4.5 Mini | Baidu | 32768 | $8.62 | 71.0 |
| OLMo 2 | Allen Institute for AI | 65536 | $2.99 | 71.0 |
FAQ
How much does Command A Mini cost?
Command A Mini is listed at $8.12 per million input tokens and $31.21 per million output tokens. Cached input is $0.70 per million tokens. A blended 3:1 input-to-output mix is about $13.89 per million tokens.
What is the context window of Command A Mini?
Command A Mini has a context window of 8,192 tokens and can emit up to 8,192 output tokens per request in this index.
Is Command A Mini open weights?
No. Command A Mini is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Command A Mini score on benchmarks?
Command A Mini averages 71.0 across the scored benchmarks in this index, ranking #347 of 600 models. Its strongest relative result is Arena Elo at 1369.4.
What is Command A Mini best for?
Command A Mini 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 $8.12 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.