ModelPriceWatch.com
Last scan 2026-08-09 Models tracked 198 Providers 30 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

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.

13 models qualify top 13 shown sorted by input price, cheapest first
1Cohere

Rerank 3.5

$0.020 /1M blended

$0.020 in · $— out · — ctx

2OpenAI

text-embedding-3-small

$0.020 /1M blended

$0.020 in · $— out · 8K ctx

3Voyage AI

rerank-2.5-lite

$0.020 /1M blended

$0.020 in · $— out · — ctx

MODELPRICEWATCH.COM · 2026-08-09

Cost calculator for this use casemonthly cost, top 3 models

1 Rerank 3.5
$—
2 text-embedding-3-small
$—
3 rerank-2.5-lite
$—

Full ranking — top 13 models

list prices, USD per 1M tokens
Top 13 models for Best Embedding Model APIs, ranked by input price, cheapest first
Model Blended* Input Output Context Provider
1Rerank 3.5 $0.020 $0.020 $— Cohere
2text-embedding-3-small $0.020 $0.020 $— 8K OpenAI
3rerank-2.5-lite $0.020 $0.020 $— Voyage AI
4voyage-4-lite $0.020 $0.020 $— Voyage AI
5rerank-2.5 $0.050 $0.050 $— Voyage AI
6voyage-4 $0.060 $0.060 $— Voyage AI
7Granite Embedding 278M Multilingual $0.106 $0.106 $— IBM
8Embed 4 $0.120 $0.120 $— Cohere
9voyage-4-large $0.120 $0.120 $— Voyage AI
10voyage-multimodal-3.5 $0.120 $0.120 $— Voyage AI
11text-embedding-3-large $0.130 $0.130 $— 8K OpenAI
12voyage-code-3 $0.180 $0.180 $— 32K Voyage AI
13voyage-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.

Other use case rankings