Embedding model for semantic search, retrieval, clustering, and ranking pipelines
text-embedding-3-large by openai is offered by 5 providers on this page. Public prices are shown for 4 of them. Its official list price is $0.13 per 1M input tokens and $0 per 1M output tokens. The lowest paid channel is SAP AI Core at $0.09 / $0 per 1M, about 1.4× below the list price.
The context window is 8,191 tokens at the reference host, but hosts report different limits, from 8,191 to 8,192, so the usable window depends on the provider you pick. Its training knowledge cuts off at 2024-01.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| SAP AI Core | Cloud | $0.09 | $0 | — | — | 8,191 | 3,072 | |
| Azure | Cloud | $0.13 | $0 | — | — | 8,192 ⚠ | 3,072 | |
| Azure Cognitive Services | Cloud | $0.13 | $0 | — | — | 8,192 ⚠ | 3,072 | |
| OpenAIOfficial | First-party | $0.13 | $0 | — | — | 8,191 | 3,072 | |
| Vercel AI Gateway | Cloud | — | — | — | — | 8,192 ⚠ | 1,536 | hostTable.undisclosed |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.