Embed v4.0 vs Embed 5 Fast
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | Embed v4.0cohere/embed-v4.0 | Embed 5 Fastcohere/embed-v5.0-fast |
|---|---|---|
| Maker | cohere | cohere |
| Kind | Embeddings | Embeddings |
| Input per 1M tokens | $0.126 | $0.084 Lower |
| Cached input per 1M tokens | Not applicable | Not applicable |
| Output per 1M tokens | Not applicable | Not applicable |
| Context window | 128,000 tokens | 128,000 tokens |
| Max output | Not applicable | Not applicable |
| Capabilities | None listed | None listed |
| Takes | Text | Text |
| Returns | Text | Text |
| Zero data retention | Not on every provider | Not on every provider |
| No training on requests | Yes, on every provider | Yes, on every provider |
| Released | 2025-04-15 | 2026-09-30 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | Embed v4.0 | Embed 5 Fast |
|---|---|---|
| 1,000 tokens | $0.000126 | $0.000084 |
| 100,000 tokens | $0.0126 | $0.0084 |