Compare OpenAI text-embedding-3-small, Cohere, Voyage AI, and Jina pricing. Enter token volume → see exact monthly cost. Free, no signup.
Select model · Enter token volume · Results update live
Cost per million tokens, June 2026.
| Model | Price / 1M tokens | Dimensions | Best for |
|---|---|---|---|
| Jina Embeddings v2CHEAPEST | $0.018 | 768 | High-volume, cost-sensitive |
| OpenAI text-3-small | $0.020 | 1536 | Best quality/cost for most RAG |
| Cohere embed-v3 | $0.100 | 1024 | Multilingual, enterprise |
| OpenAI ada-002 | $0.100 | 1536 | Legacy, being phased out |
| Voyage AI voyage-2 | $0.120 | 1024 | Code search, technical docs |
| OpenAI text-3-large | $0.130 | 3072 | Max quality, high-precision RAG |
Store your embeddings — start free:
text-embedding-3-small costs $0.020 per million tokens (cheapest OpenAI option). text-embedding-3-large costs $0.130/M. For 100K documents at ~300 tokens each (30M tokens), text-3-small costs $0.60 total.
Jina Embeddings v2 at $0.018/M tokens is cheapest. OpenAI text-3-small at $0.020/M is close and has excellent quality. For self-hosted, sentence-transformers (free) on a $6/mo Hetzner VPS is near-zero cost at scale.
1536 dimensions (OpenAI text-3-small default) works well for most RAG use cases. You can truncate OpenAI text-3-small to 512 or 256 dimensions with minimal quality loss and significant storage savings. Only use 3072-dim for very high-precision retrieval needs.
Typical documents: 100-word paragraph ~133 tokens, 1-page document ~700 tokens, 10-page report ~7,000 tokens. Most embedding models have 8,191 token input limits — chunk longer documents.