Very long inputs
Choose Codestral Embed
Codestral Embed reads up to 8k tokens per request, against 512 for Embed Multilingual v3.0.
Choose Codestral Embed 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 Codestral Embed
Codestral Embed reads up to 8k tokens per request, against 512 for Embed Multilingual v3.0.
Choose Codestral Embed
Codestral Embed is the newer release (May 2025, against November 2023 for Embed Multilingual v3.0).
| Codestral Embed | Embed Multilingual v3.0 | |
|---|---|---|
| Provider | Mistral AI | Cohere |
| Category | Embeddings | Embeddings |
| Status | Generally available | Legacy |
| Headline price | No data | No data |
| Context window | 8k | 512 |
| Max output | No data | No data |
| Released | May 2025 | November 2023 |
| Knowledge cutoff | No data | No data |
| Licence | Proprietary | Proprietary |
| Capabilities | No data | No data |
| API model id | codestral-embed-2505 | embed-multilingual-v3.0 |
Choose Codestral Embed 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.
Codestral Embed reads more per request: 8k tokens against 512.
Codestral Embed is made by Mistral AI and Embed Multilingual v3.0 by Cohere. A price comparison is not possible: one of them has no comparable published price. Codestral Embed reads more per request: 8k tokens against 512. Codestral Embed is the newer model (May 2025, against November 2023).
Codestral Embed was released on May 2025 and Embed Multilingual v3.0 on November 2023.