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.
12 models qualify
top 12 shown
sorted by input price, cheapest first
MODELPRICEWATCH.COM · 2026-10-17
Cost calculator for this use casemonthly cost, top 3 models
- 1 text-embedding-3-small
- $—
- 2 rerank-2.5-lite
- $—
- 3 voyage-4-lite
- $—
Full ranking — top 12 models
list prices, USD per 1M tokens| Model | Blended* | Input | Output | Context | Provider |
|---|---|---|---|---|---|
| 1text-embedding-3-small | $0.020 | $0.020 | — | 8K | OpenAI |
| 2rerank-2.5-lite | $0.020 | $0.020 | — | — | Voyage AI |
| 3voyage-4-lite | $0.020 | $0.020 | — | — | Voyage AI |
| 4rerank-2.5 | $0.050 | $0.050 | — | — | Voyage AI |
| 5voyage-4 | $0.060 | $0.060 | — | — | Voyage AI |
| 6Granite Embedding 278M Multilingual | $0.106 | $0.106 | — | — | IBM |
| 7Embed 4 | $0.120 | $0.120 | — | — | Cohere |
| 8voyage-4-large | $0.120 | $0.120 | — | — | Voyage AI |
| 9voyage-multimodal-3.5 | $0.120 | $0.120 | — | — | Voyage AI |
| 10text-embedding-3-large | $0.130 | $0.130 | — | 8K | OpenAI |
| 11voyage-code-3 | $0.180 | $0.180 | — | 32K | Voyage AI |
| 12voyage-context-3 | $0.180 | $0.180 | — | 32K | Voyage AI |
Ranking basis: input price, cheapest first. * Blended = (3×input + 1×output) ÷ 4. Every price links to its source on the model page.
How models are selected
Embedding-category models, sorted by input price per million tokens.
Prices are per million tokens (Mtok), sourced directly from — and linked to — official provider pricing pages. "Blended cost" is (3×input + 1×output) ÷ 4 — weighted toward input because real workloads read far more tokens than they generate.