Very long inputs
Choose Command A Vision
Command A Vision reads up to 128k tokens per request, against 8k for computer-use-preview.
Choose Command A Vision for very long inputs and the latest release; on the other points the two are level or the data is missing.
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Choose Command A Vision
Command A Vision reads up to 128k tokens per request, against 8k for computer-use-preview.
Choose Command A Vision
Command A Vision is the newer release (July 2025, against Mar 11, 2025 for computer-use-preview).
| Command A Vision | computer-use-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 | 128k | 8k |
| Max output | No data | 1k |
| Released | July 2025 | Mar 11, 2025 |
| Knowledge cutoff | No data | October 2023 |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision | Vision, Tool calling, Structured output, Batch API |
| API model id | command-a-vision-07-2025 | computer-use-preview |
Choose Command A Vision for very long inputs and the latest release; on the other points the two are level or the data is missing.
A price comparison is not possible: one of them has no comparable published price.
Command A Vision reads more per request: 128k tokens against 8k.
Command A Vision is made by Cohere and computer-use-preview by OpenAI. A price comparison is not possible: one of them has no comparable published price. Command A Vision reads more per request: 128k tokens against 8k. Command A Vision is the newer model (July 2025, against Mar 11, 2025). Only computer-use-preview offers tool calling, structured output, batch api.
Command A Vision was released on July 2025 and computer-use-preview on Mar 11, 2025.