# BGE M3 API Pricing

As of October 10, 2026, BGE M3 costs $0.01 per 1M input tokens from LibertAI, the lowest of 2 providers. It has an 8,192-token context window and returns up to 96,000 tokens per response.

- Page: https://models.litellm.ai/models/bge-m3
- LiteLLM model name: `libertai/bge-m3`
- Context window: 8,192 tokens
- Max output: 96,000 tokens
- Added to LiteLLM: January 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| LibertAI | `libertai/bge-m3` | $0.01 | $0 | – | – | – | 8K |
| Novita AI | `novita/baai/bge-m3` | $0.01 | $0.01 | – | – | – | 8K |

## Cost examples

Embedding 10,000 documents of 500 tokens each:

- LibertAI: $0.05
- Novita AI: $0.05

## Use it with LiteLLM

```python
from litellm import embedding

response = embedding(
    model="libertai/bge-m3",
    input=["hello world"],
)
```

## FAQ

### How much does BGE M3 cost?

BGE M3 costs $0.01 per 1M input tokens from LibertAI, the lowest of 2 providers.

### What is the context window of BGE M3?

BGE M3 has an 8,192-token context window and returns up to 96,000 tokens per response.

### Which providers offer BGE M3?

BGE M3 is available from 2 providers through LiteLLM: LibertAI and Novita AI.

### How do I call BGE M3 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="libertai/bge-m3", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/embeddings from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### When did LiteLLM add BGE M3?

BGE M3 was added to LiteLLM's model price file in January 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json