Embedding model for semantic search, retrieval, clustering, and ranking pipelinesGemini Embedding 001 by google is offered by 5 providers on this page. Public prices are shown for 3 of them. Its official list price is $0.15 per 1M input tokens and $0 per 1M output tokens. No paid channel is priced below the official list price.
The context window is 2,048 tokens, with an output limit of 1 tokens. Its training knowledge cuts off at 2025-05.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| VertexOfficial | Cloud | $0.15 | $0 | — | — | 2,048 | 1 | |
| GoogleOfficial | First-party | $0.15 | $0 | — | — | 2,048 | 1 | |
| Merge Gateway | Gateway | $0.15 | $0 | — | — | 2,048 | — | |
| SAP AI Core gemini-embedding | Cloud | — | — | — | — | 2,048 | 1 | hostTable.undisclosed |
| Vercel AI Gateway | Cloud | — | — | — | — | 2,048 | 1 | 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.