BGE-M3

BAAI's multilingual embedding model supporting dense, sparse, and multi-vector retrieval across 100+ languages. 8K context, 1024-dim output.

bge-m3
Embedding modelSTABLEGet StartedView uptime
8,192 context
Released January 29, 2024
Starting at $0.01/M input tokens
Starting at $0.00/M output tokens
Embeddings
No ratings yetSign in to rate

Select Provider

All Providers for BGE-M3

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

DeepInfra
Context: 8.2k
Input
$0.01
/M tokens
Cache Read
/M tokens
Output
$0
/M tokens
Get Started

Frequently asked questions

What is BGE-M3?

BAAI's multilingual embedding model supporting dense, sparse, and multi-vector retrieval across 100+ languages. 8K context, 1024-dim output. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does BGE-M3 cost?

Pricing for BGE-M3 on LLM Gateway starts at $0.01 per million input tokens and $0.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of BGE-M3?

BGE-M3 supports a context window of up to 8,192 tokens on its largest provider deployment.

Which providers serve BGE-M3?

BGE-M3 is served by DeepInfra through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does BGE-M3 support tool calling and structured outputs?

No. BGE-M3 does not currently support tool calling or structured JSON outputs through LLM Gateway.

When was BGE-M3 released?

BGE-M3 was released on January 29, 2024.