Voyage 4 Nano measured on 7 of 261 Embeddings benchmarks7
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
46MTEB Thai v1
Jan 2026released
1,024Dimensions
33K tokensMax input
Alternatives?
ModelScoreCostPriceWhat changes
BetterBge M3unstatedOpen+15%—$0.01Max input: 33K tokens → 8K tokens+1cOpenF2LLM v2 8Bunstated+52%——Memory (4-bit): 0.2 GB → 4.5 GB
BetterQwen 3 Embedding 0.6BunstatedOpen+5%—$0.01Memory (4-bit): 0.2 GB → 0.4 GBBetterQwen 3 Embedding 4BunstatedOpen+12%—$0.02Memory (4-bit): 0.2 GB → 2.4 GBcBetterF2LLM v2 14BunstatedOpen+53%——Memory (4-bit): 0.2 GB → 8.4 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Bge M3unstatedOpen+15%—$0.01Max input: 33K tokens → 8K tokens+1Qwen 3 Embedding 0.6BunstatedOpen+5%—$0.01Memory (4-bit): 0.2 GB → 0.4 GBQwen 3 Embedding 4BunstatedOpen+12%—$0.02Memory (4-bit): 0.2 GB → 2.4 GBcF2LLM v2 14BunstatedOpen+53%——Memory (4-bit): 0.2 GB → 8.4 GBcF2LLM v2 8BunstatedOpen+52%——Memory (4-bit): 0.2 GB → 4.5 GBModelScoreCostPriceWhat changes
cF2LLM v2 8BunstatedOpen+52%——Memory (4-bit): 0.2 GB → 4.5 GBcF2LLM v2 4BunstatedOpen+51%——Memory (4-bit): 0.2 GB → 2.4 GBcF2LLM v2 1.7BunstatedOpen+51%——Memory (4-bit): 0.2 GB → 1 GBhBekko Embedding v1 A25munstatedOpen+49%——Max input: 33K tokens → 8K tokenscF2LLM v2 0.6BunstatedOpen+47%——Memory (4-bit): 0.2 GB → 0.4 GBModelScoreCostPriceWhat changes
VVoyage 4n/a—$0.06Max input: 33K tokens → 32K tokensVVoyage 4 Largeunstatedn/a—$0.12Max input: 33K tokens → 32K tokensVVoyage 4 Liten/a—$0.02Max input: 33K tokens → 32K tokensVMdbr Leaf IrOpenn/a——Max input: 33K tokens → 1K tokensVMdbr Leaf MTunstatedOpenn/a——Max input: 33K tokens → 1K tokensVVoyage 3.5unstatedn/a—$0.06Max input: 33K tokens → 32K tokensVVoyage 3 M Expunstatedn/a——Max input: 33K tokens → 32K tokensVVoyage 3 Largen/a—$0.18Max input: 33K tokens → 32K tokensAll Voyage AI (MongoDB) models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does Voyage 4 Nano cost?›
There is no per-unit API price: self-host only.
Is Voyage 4 Nano free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Voyage 4 Nano, and what is it best at?›
#45 of 191 in Embeddings.
Is Voyage 4 Nano better than PIXIE Rune v1.0?›
On MTEB Thai v1 · Reranking · Thai, Voyage 4 Nano scores 54.9 vs 55.4 — about the same.
When was Voyage 4 Nano released? Is there a newer version?›
Released 2026-01-15. It is the current version in its line.
Is Voyage 4 Nano open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Voyage 4 Nano locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Voyage 4 Nano?›
Voyage 4 Nano is an open-weights embeddings & retrieval model from Voyage AI (MongoDB), released Jan 2026.
What are the best alternatives to Voyage 4 Nano?›
Bge M3 (better), F2LLM v2 8B (open weights).