What is the context window of BGE M3 by Nvidia?

BGE M3 by Nvidia has a context window of 8K tokens. It supports up to 8K input tokens and can generate up to 1K output tokens.

What input and output types does BGE M3 support?

BGE M3 by Nvidia accepts text as input and can generate text as output.

Is BGE M3 by Nvidia open source?

Yes, BGE M3 by Nvidia has open weights, meaning the model weights are publicly available for download and self-hosting.

Back to Models

BGE M3 API

Nvidia

About

BGE M3 is a high-performance LLM available via the Nvidia API, ideal for scalable text generation and natural language processing. This model delivers available completely free of charge, open weights architecture. Access BGE M3 via the Nvidia API with up to 1K output tokens.

Capabilities

Input Modalities

text

Output Modalities

text

Reasoning

Structured Output

Tool Use

WeightsOpen

Temperature

Fixed

Attachment

Not Supported

Limits

Context Window

Tokens

Input Limit

Tokens

Max Output

Tokens

Pricing

Standard (per 1M tokens)

Input

Free

Output

Free

Frequently Asked Questions

BGE M3 by Nvidia costs Free per 1M input tokens and Free per 1M output tokens.

Model Details

baai/bge-m3

Provider

Nvidia

Family

bge

Release Date

Jan 30, 2024

Knowledge Cutoff

N/A

API Integration

NPM Package

@ai-sdk/openai-compatible

Environment Variables

NVIDIA_API_KEY

API Base URL

https://integrate.api.nvidia.com/v1

Documentation