Very long inputs
Choose Command A
Command A reads up to 256k tokens per request, against 128k for Aya Expanse 32B.
Aya Expanse 32B vs Command A: price, context and capabilities
Choose Aya Expanse 32B for self-hosting and data control. Choose Command A for very long inputs and the latest release.
In short
- A price comparison is not possible: one of them has no comparable published price.
- Command A reads more per request: 256k tokens against 128k.
- Command A is the newer model (March 2025, against October 2024).
- Only Aya Expanse 32B offers self-hostable.
- Only Command A offers tool calling, structured output.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Self-hosting and data control
Choose Aya Expanse 32B
Aya Expanse 32B has open weights, so you can run it on your own servers; Command A is only available through its provider.
Latest release
Choose Command A
Command A is the newer release (March 2025, against October 2024 for Aya Expanse 32B).
Specifications side by side
| Aya Expanse 32B | Command A | |
|---|---|---|
| Provider | Cohere | Cohere |
| Category | Language models | Language models |
| Status | Generally available | Generally available |
| Headline price | No data | No data |
| Input | No data | No data |
| Output | No data | No data |
| Cached input | No data | No data |
| Context window | 128k | 256k |
| Max output | No data | No data |
| Released | October 2024 | March 2025 |
| Knowledge cutoff | No data | No data |
| Licence | Open weights | Proprietary |
| Capabilities | Self-hostable | Tool calling, Structured output |
| API model id | c4ai-aya-expanse-32b | command-a-03-2025 |
Benchmarks side by side
Leader in bold.
| Benchmark | Aya Expanse 32B | Command A |
|---|---|---|
| Terminal-Bench Hard | No data | 0.8% |
| GPQA Diamond | No data | 52.7% |
| Humanity's Last Exam | No data | 4% |
| IFBench (instruction following) | No data | 36.5% |
| τ²-Bench (agentic tool use) | No data | 15.2% |
| Long-context reasoning (AA-LCR) | No data | 21.3% |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Frequently asked questions
Should I choose Aya Expanse 32B or Command A?
Choose Aya Expanse 32B for self-hosting and data control. Choose Command A for very long inputs and the latest release.
Which is cheaper, Aya Expanse 32B or Command A?
A price comparison is not possible: one of them has no comparable published price.
Which has the larger context window, Aya Expanse 32B or Command A?
Command A reads more per request: 256k tokens against 128k.
What is the difference between Aya Expanse 32B and Command A?
Aya Expanse 32B is made by Cohere and Command A by Cohere. A price comparison is not possible: one of them has no comparable published price. Command A reads more per request: 256k tokens against 128k. Command A is the newer model (March 2025, against October 2024). Only Aya Expanse 32B offers self-hostable. Only Command A offers tool calling, structured output.
Which is newer, Aya Expanse 32B or Command A?
Command A was released on March 2025 and Aya Expanse 32B on October 2024.