Very long inputs
Choose Command R7B
Command R7B reads up to 128k tokens per request, against 8k for computer-use-preview.
Choose Command R7B for very long inputs. Choose computer-use-preview for images as input and the latest release.
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Choose Command R7B
Command R7B reads up to 128k tokens per request, against 8k for computer-use-preview.
Choose computer-use-preview
computer-use-preview accepts images as input; Command R7B does not.
Choose computer-use-preview
computer-use-preview is the newer release (Mar 11, 2025, against December 2024 for Command R7B).
| Command R7B | 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 | December 2024 | Mar 11, 2025 |
| Knowledge cutoff | No data | October 2023 |
| Licence | Proprietary | Proprietary |
| Capabilities | Tool calling | Vision, Tool calling, Structured output, Batch API |
| API model id | command-r7b-12-2024 | computer-use-preview |
Choose Command R7B for very long inputs. Choose computer-use-preview for images as input and the latest release.
A price comparison is not possible: one of them has no comparable published price.
Command R7B reads more per request: 128k tokens against 8k.
Command R7B 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 R7B reads more per request: 128k tokens against 8k. computer-use-preview is the newer model (Mar 11, 2025, against December 2024). Only computer-use-preview offers vision, structured output, batch api.
computer-use-preview was released on Mar 11, 2025 and Command R7B on December 2024.