Voyage 4 Nano measured on 7 of 194 Embeddings benchmarks7
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
61.9MTEB Thai v1
Jan 2026released
1,024Dimensions
33K tokensMax input
Alternatives?
ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+27%—$0.01Memory (4-bit): 0.2 GB → 4.5 GBcOpenF2LLM v2 8Bunstated×2——Memory (4-bit): 0.2 GB → 4.5 GBiBetterMultilingual E5 Large InstructunstatedOpen+22%—$0.01Max input: 33K tokens → 1K tokens+1BetterQwen 3 Embedding 0.6BunstatedOpen+14%—$0.01Memory (4-bit): 0.2 GB → 0.4 GB
BetterJina Embeddings v5 Text NanounstatedOpen+24%—$0.02Max input: 33K tokens → 8K tokensModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+27%—$0.01Memory (4-bit): 0.2 GB → 4.5 GBiMultilingual E5 Large InstructunstatedOpen+22%—$0.01Max input: 33K tokens → 1K tokens+1Qwen 3 Embedding 0.6BunstatedOpen+14%—$0.01Memory (4-bit): 0.2 GB → 0.4 GBJina Embeddings v5 Text NanounstatedOpen+24%—$0.02Max input: 33K tokens → 8K tokensQwen 3 Embedding 4BunstatedOpen+18%—$0.02Memory (4-bit): 0.2 GB → 2.4 GBModelScoreCostPriceWhat changes
cF2LLM v2 8BunstatedOpen×2——Memory (4-bit): 0.2 GB → 4.5 GBcF2LLM v2 1.7BunstatedOpen+100%——Memory (4-bit): 0.2 GB → 1 GBcF2LLM v2 4BunstatedOpen+99%——Memory (4-bit): 0.2 GB → 2.4 GBcF2LLM v2 0.6BunstatedOpen+97%——Memory (4-bit): 0.2 GB → 0.4 GBcF2LLM v2 330MunstatedOpen+86%——ModelScoreCostPriceWhat changes
VVoyage 3.5unstated-4%—$0.06Max input: 33K tokens → 32K tokensVVoyage Multilingual 2unstated-5%—$0.12Max input: 33K tokens → 32K tokensVVoyage 3 Liteunstated-14%—$0.02Max input: 33K tokens → 32K tokensVVoyage 3unstated-17%—$0.06Max input: 33K tokens → 32K tokensVVoyage Large 2 Instructunstated-41%—$0.12Max input: 33K tokens → 16K tokensVVoyage 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 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?›
#14 of 26 in Embeddings.
Is Voyage 4 Nano better than Nomic Embed Text v2 Moe?›
On MTEB Thai v1 · Clustering · Thai, Voyage 4 Nano scores 46 vs 46.2 — 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?›
Qwen 3 Embedding 8B (better), F2LLM v2 8B (open weights).