Very long inputs
Choose Command R7B
Command R7B reads up to 128k tokens per request, against 16k for davinci-002.
Choose Command R7B 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 R7B
Command R7B reads up to 128k tokens per request, against 16k for davinci-002.
Choose Command R7B
Command R7B is the newer release (December 2024, against August 2023 for davinci-002).
| Command R7B | davinci-002 | |
|---|---|---|
| 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 | 16k |
| Max output | No data | No data |
| Released | December 2024 | August 2023 |
| Knowledge cutoff | No data | September 2021 |
| Licence | Proprietary | Proprietary |
| Capabilities | Tool calling | Structured output, Batch API |
| API model id | command-r7b-12-2024 | davinci-002 |
Choose Command R7B 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 R7B reads more per request: 128k tokens against 16k.
Command R7B is made by Cohere and davinci-002 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 16k. Command R7B is the newer model (December 2024, against August 2023). Only Command R7B offers tool calling. Only davinci-002 offers structured output, batch api.
Command R7B was released on December 2024 and davinci-002 on August 2023.