Very long inputs
Choose Command A
Command A reads up to 256k tokens per request, against 128k for o1 Preview.
Command A vs o1 Preview: price, context and capabilities
Choose Command A for very long inputs and the latest release. Choose o1 Preview for images as input.
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 Sep 12, 2024).
- Only o1 Preview offers vision, reasoning, batch api.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Images as input
Choose o1 Preview
o1 Preview accepts images as input; Command A does not.
Latest release
Choose Command A
Command A is the newer release (March 2025, against Sep 12, 2024 for o1 Preview).
Specifications side by side
| Command A | o1 Preview | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Category | Language models | Language models |
| Status | Generally available | Deprecated |
| Headline price | No data | No data |
| Input | No data | No data |
| Output | No data | No data |
| Cached input | No data | No data |
| Context window | 256k | 128k |
| Max output | No data | 33k |
| Released | March 2025 | Sep 12, 2024 |
| Knowledge cutoff | No data | October 2023 |
| Licence | Proprietary | Proprietary |
| Capabilities | Tool calling, Structured output | Vision, Reasoning, Tool calling, Structured output, Batch API |
| API model id | command-a-03-2025 | o1-preview |
Benchmarks side by side
Leader in bold.
| Benchmark | Command A | o1 Preview |
|---|---|---|
| GPQA Diamond | 52.7% | 76.5% |
| Terminal-Bench Hard | 0.8% | No data |
| Humanity's Last Exam | 4% | No data |
| IFBench (instruction following) | 36.5% | No data |
| τ²-Bench (agentic tool use) | 15.2% | No data |
| Long-context reasoning (AA-LCR) | 21.3% | No data |
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 Command A or o1 Preview?
Choose Command A for very long inputs and the latest release. Choose o1 Preview for images as input.
Which is cheaper, Command A or o1 Preview?
A price comparison is not possible: one of them has no comparable published price.
Which has the larger context window, Command A or o1 Preview?
Command A reads more per request: 256k tokens against 128k.
What is the difference between Command A and o1 Preview?
Command A is made by Cohere and o1 Preview by OpenAI. 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 Sep 12, 2024). Only o1 Preview offers vision, reasoning, batch api.
Which is newer, Command A or o1 Preview?
Command A was released on March 2025 and o1 Preview on Sep 12, 2024.