i

E5 Base v2

Feb 2024
iE5 Base v2
Compare in
on
$0.005per 1M tokens
49.7MTEB English v2
Feb 2024released
768Dimensions
1K tokensMax input
enLanguages

Alternatives?

Run it yourself

estimate
Fits 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
LicenceMITfree for commercial use

History

2 versions
8585.285.485.6Jan 23Apr 23Jul 23Oct 23Jan 24Release dateMTEB English · Pair ClassificationE5 · DecE5 · Feb
8585.285.485.6Jan 23Jul 23Jan 24Release dateMTEB English · Pair ClassificationE5 · Dec

Benchmarks

in Embeddings & Retrieval

FAQ

How much does E5 Base v2 cost?›

$0.005 per 1M tokens.

Is E5 Base v2 free to use?›

There is no free API; the cheapest paid price is $0.005 per 1M input tokens. The weights are open, so you can run it yourself.

How good is E5 Base v2, and what is it best at?›

#108 of 200 in Embeddings.

Is E5 Base v2 better than E5 Base 4K?›

On MTEB English v2 · Pair Classification · English, E5 Base v2 scores 85.6 vs 85.7 — about the same.

How can I use E5 Base v2?›

Through the intfloat API.

When was E5 Base v2 released? Is there a newer version?›

Released 2024-02-08. It is the current version in its line.

Is E5 Base v2 open source?›

Yes, the weights are open (MIT licence).

Can I run E5 Base v2 locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

What is E5 Base v2?›

E5 Base v2 is an open-weights embeddings & retrieval model from intfloat, released Feb 2024.

What are the best alternatives to E5 Base v2?›

EmbeddingGemma 300M (cheaper), Bge En Icl (better), QZhou Embedding (open weights).