Best Embedding Model APIs
Compare embedding model APIs for RAG pipelines and semantic search. Find the cheapest and most capable embedding models for vector databases.
Cost calculator for this use case
🥇 Rerank 3.5
$—
🥈 text-embedding-3-small
$—
🥉 rerank-2.5-lite
$—
Full ranking — top 14 models
| # | Model | Provider | Input $/Mtok | Output $/Mtok | Blended | Context | |
|---|---|---|---|---|---|---|---|
| 1 | Rerank 3.5 | Cohere | $0.020 | $0.020 | $0.020 | — | → |
| 2 | text-embedding-3-small | OpenAI | $0.020 | $0.020 | $0.020 | 8K | → |
| 3 | rerank-2.5-lite | Voyage AI | $0.020 | $0.020 | $0.020 | — | → |
| 4 | voyage-4-lite | Voyage AI | $0.020 | $0.020 | $0.020 | — | → |
| 5 | text-embedding-004 | $0.025 | $0.025 | $0.025 | 2K | → | |
| 6 | rerank-2.5 | Voyage AI | $0.050 | $0.050 | $0.050 | — | → |
| 7 | voyage-4 | Voyage AI | $0.060 | $0.060 | $0.060 | — | → |
| 8 | Granite Embedding 278M Multilingual | IBM | $0.106 | $0.106 | $0.106 | — | → |
| 9 | Embed 4 | Cohere | $0.120 | $0.120 | $0.120 | — | → |
| 10 | voyage-4-large | Voyage AI | $0.120 | $0.120 | $0.120 | — | → |
| 11 | voyage-multimodal-3.5 | Voyage AI | $0.120 | $0.120 | $0.120 | — | → |
| 12 | text-embedding-3-large | OpenAI | $0.130 | $0.130 | $0.130 | 8K | → |
| 13 | voyage-code-3 | Voyage AI | $0.180 | $0.180 | $0.180 | 32K | → |
| 14 | voyage-context-3 | Voyage AI | $0.180 | $0.180 | $0.180 | 32K | → |
How models are selected
Embedding-category models, sorted by input price per million tokens.
Prices are per million tokens (Mtok), sourced directly from official provider pricing pages and verified by our automated scraper pipeline that runs 3x daily. "Blended cost" is the average of input and output pricing — a quick proxy for typical 50/50 usage patterns.