Very long inputs
Choose Command A
Command A reads up to 256k tokens per request, against 128k for Command R7B.
Command A vs Command R7B: price, context and capabilities
Choose Command A for very long inputs and the latest release; on the other points the two are level or the data is missing.
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 December 2024).
- Only Command A offers structured output.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Latest release
Choose Command A
Command A is the newer release (March 2025, against December 2024 for Command R7B).
Specifications side by side
| Command A | Command R7B | |
|---|---|---|
| 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 | 256k | 128k |
| Max output | No data | No data |
| Released | March 2025 | December 2024 |
| Knowledge cutoff | No data | No data |
| Licence | Proprietary | Proprietary |
| Capabilities | Tool calling, Structured output | Tool calling |
| API model id | command-a-03-2025 | command-r7b-12-2024 |
Benchmarks side by side
Leader in bold.
| Benchmark | Command A | Command R7B |
|---|---|---|
| Terminal-Bench Hard | 0.8% | No data |
| GPQA Diamond | 52.7% | 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 Command R7B?
Choose Command A for very long inputs and the latest release; on the other points the two are level or the data is missing.
Which is cheaper, Command A or Command R7B?
A price comparison is not possible: one of them has no comparable published price.
Which has the larger context window, Command A or Command R7B?
Command A reads more per request: 256k tokens against 128k.
What is the difference between Command A and Command R7B?
Command A is made by Cohere and Command R7B 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 December 2024). Only Command A offers structured output.
Which is newer, Command A or Command R7B?
Command A was released on March 2025 and Command R7B on December 2024.