e5-base-v2

Name: e5-base-v2
Author: DeepInfra

embedmit

Text Embeddings by Weakly-Supervised Contrastive Pre-training. Model has 24 layers and 1024 out dim.

Capabilities

Show unsupported (7)

Infrastructure

Fine-tuning

Model IDintfloat/e5-base-v2

Creatorintfloat

Familye5

Licensemit

Statusactive

Typeembed

Input modalitiestext

Output modalitiesembedding

Open weightYes

Parameters—

Architecture—

Context window—

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date—

Sourceofficial

EmbeddingsPOST

Generate vector embeddings for texthttps://api.deepinfra.com/v1/openai/v1/embeddings

Model	Caps	Perf	Speed	Context	Max out
e5-base-v2	F	—	—	—	—
e5-large-v2	F	—	—	—	—
multilingual-e5-large-instruct	F	—	—	—	—
multilingual-e5-large	F	—	—	—	—

GET/v1/models/deepinfra/intfloat/e5-base-v2