Very long inputs
Choose text-embedding-3-small
text-embedding-3-small reads up to 8k tokens per request, against 512 for Embed Multilingual v3.0.
Choose text-embedding-3-small 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 text-embedding-3-small
text-embedding-3-small reads up to 8k tokens per request, against 512 for Embed Multilingual v3.0.
Choose text-embedding-3-small
text-embedding-3-small is the newer release (January 2024, against November 2023 for Embed Multilingual v3.0).
| Embed Multilingual v3.0 | text-embedding-3-small | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Category | Embeddings | Embeddings |
| Status | Legacy | Generally available |
| Headline price | No data | $0.02 / 1M tokens |
| Context window | 512 | 8k |
| Max output | No data | No data |
| Released | November 2023 | January 2024 |
| Knowledge cutoff | No data | No data |
| Licence | Proprietary | Proprietary |
| Capabilities | No data | No data |
| API model id | embed-multilingual-v3.0 | text-embedding-3-small |
Choose text-embedding-3-small 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.
text-embedding-3-small reads more per request: 8k tokens against 512.
Embed Multilingual v3.0 is made by Cohere and text-embedding-3-small by OpenAI. A price comparison is not possible: one of them has no comparable published price. text-embedding-3-small reads more per request: 8k tokens against 512. text-embedding-3-small is the newer model (January 2024, against November 2023).
text-embedding-3-small was released on January 2024 and Embed Multilingual v3.0 on November 2023.