text-embedding-ada-002 vs text-embedding-3-small
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 | text-embedding-ada-002openai/text-embedding-ada-002 | text-embedding-3-smallopenai/text-embedding-3-small |
|---|---|---|
| Maker | openai | openai |
| Kind | Embeddings | Embeddings |
| Input per 1M tokens | $0.105 | $0.021 Lower |
| Cached input per 1M tokens | Not applicable | Not applicable |
| Output per 1M tokens | Not applicable | Not applicable |
| Context window | Not published | Not published |
| 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 | 2022-12-15 | 2024-01-25 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | text-embedding-ada-002 | text-embedding-3-small |
|---|---|---|
| 1,000 tokens | $0.000105 | $0.000021 |
| 100,000 tokens | $0.0105 | $0.0021 |