Jahanzaib
BAAI: BGE M3

BAAI: BGE M3

byBAAI

BGE M3 is an embedding model from BAAI released on Jan 30, 2024. It reads text and writes vectors, with a 8K token context window.

Show more

It costs $0.01 per million input tokens, with no charge for output.

Its weights are open, so you can host it yourself.

2 providers serve it, including Novita AI and DigitalOcean.

Modalities
In / out price
$0.01 / $0 per 1M
Context
8K
Max output
n/a
Released
Jan 30, 2024
Knowledge cutoff
n/a
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

BGE M3 pricing

USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$0.01 / 1M tokens
Output$0 / 1M tokens

BGE M3 providers

2 providers serve it, including Novita AI and DigitalOcean. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.

ProviderInput /MOutput /MCache read /MContextMax output
Novita AI$0.01$0–8Kn/a
DigitalOcean$0.02$0–8K1K

What BGE M3 costs per month

Pick a workload close to yours or type your own volumes.

BGE M3 per month
$0.75
Without caching
$0.75
Per request
$0.00

Alternatives to BGE M3

Models that take the same inputs, closest in price, cheaper ones first.

  • Qwen 3 Embedding 4B

    Embeddings

    Turns text into vectors for search and retrieval. Served by 3 providers.

    by qwenJan 1, 2025$0.01/M input tokens3 providers

  • Qwen3 Embedding 8B

    Embeddings

    Turns text into vectors for search and retrieval. Served by 8 providers.

    by qwenJan 1, 2025$0.01/M input tokens8 providers

  • Qwen3 Embedding 0.6B

    Embeddings

    Turns text into vectors for search and retrieval. Served by 3 providers.

    by qwenJun 3, 2025$0.01/M input tokens$0.01/M output tokens3 providers

  • OpenAI: text-embedding-3-small

    Embeddings

    Turns text into vectors for search and retrieval. Served by 5 providers.

    by openaiJan 25, 2024$0.02/M input tokens5 providers

  • Mistral Embed

    Embeddings

    Turns text into vectors for search and retrieval. Served by 3 providers.

    by mistralaiDec 11, 2023$0.10/M input tokens3 providers

  • OpenAI: text-embedding-ada-002

    Embeddings

    Turns text into vectors for search and retrieval. Served by 4 providers.

    by openaiDec 15, 2022$0.10/M input tokens4 providers

More from BAAI

  • BGE Reranker V2 M3

    Rerank

    Reorders search results by relevance to a query. Served by 2 providers.

    by baaiMar 12, 2024$0.01/M input tokens2 providers

All BAAI models

BGE M3 questions

How much does the BGE M3 API cost?

$0.01 per million input tokens and $0 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of BGE M3?

8,192 tokens of input. As a rough guide, a million tokens is around 750,000 English words.

Which providers serve BGE M3?

2 providers serve it, including Novita AI and DigitalOcean. Prices differ by host, so the Providers table on this page lists each one with its input and output price.

Is BGE M3 open source?

Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.

When was BGE M3 released?

Jan 30, 2024.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.