Best embedding models for RAG and search
Embeddings power semantic search and retrieval-augmented generation. Compare OpenAI and Google embedding models by live price.
Ordered from lowest price
Live TokenRex prices. Per 1M tokens for chat and embeddings; per unit for media.
| # | Model | Input | Output / unit |
|---|---|---|---|
| 1 | Text Embedding 3 Small text-embedding-3-small | $0.02 | — |
| 2 | Text Embedding 3 Large text-embedding-3-large | $0.13 | — |
| 3 | Gemini Embedding 001 gemini-embedding-001 | $0.15 | — |
| 4 | Gemini Embedding 2 gemini-embedding-2 | $0.20 | — |
How to choose
- Embed your documents once and store the vectors — you pay only for new text.
- Use the same embedding model for indexing and querying.
Try it with one API key
Use the endpoint for the model’s actual type, not Chat Completions. Images, video, speech, embeddings and live audio have different request formats. Open the model page and Docs before submitting your first request.
Head-to-head comparisons
Questions
- How are these embedding models ranked?
- Models are listed from the live TokenRex catalog and ordered by current price. We do not publish invented quality scores; open a model page for source-linked benchmarks where they exist.
- Can I switch models later?
- Yes. Every model uses the same TokenRex API key and endpoint, so switching is a one-line change to the model ID.
- Do prices include a markup?
- Prices shown are the live TokenRex rates billed from your wallet. They update automatically when provider prices change.