BGE Large EN v1.5

BAAI · 335M params · 512 context

Deploy this modelrocket_launch
P
Parthexpand_more

About

State-of-the-art English embedding model for retrieval and search.

Type

Embedding

Parameters

335M params

Context

512

License

MIT

Recommended deployment

memory

Best quality

RTX 4090 x8 · 12k tok/s

$26.4

/hour

memory

Balanced

A100 SXM x4 · 6k tok/s

$6.6

/hour

memory

Budget

RTX 4090 x2 · 2k tok/s

$1.1

/hour

Pricing

Input tokens

$0.02

per 1M tokens

Output tokens

$0.00

per 1M tokens

Quick stats

Deploys

4,210

Recommended GPU

RTX 4090

Inference latency

~280ms P50

Throughput

~12k tok/s

Use cases

  • check_circleCustomer support automation
  • check_circleKnowledge base search
  • check_circleAgentic workflows
  • check_circleContent generation