# Llama Prompt Guard 2 86M API Pricing

As of October 10, 2026, Llama Prompt Guard 2 86M costs $0.04 per 1M input tokens and $0.04 per 1M output tokens on Groq. It has a 512-token context window and returns up to 512 tokens per response.

- Page: https://models.litellm.ai/models/llama-prompt-guard-2-86m
- Lab: Meta
- LiteLLM model name: `groq/meta-llama/llama-prompt-guard-2-86m`
- Context window: 512 tokens
- Max output: 512 tokens
- Added to LiteLLM: August 13, 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 |
|---|---|---|---|---|---|---|---|
| Groq | `groq/meta-llama/llama-prompt-guard-2-86m` | $0.04 | $0.04 | – | – | – | 512 |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Groq: $0.10

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="groq/meta-llama/llama-prompt-guard-2-86m",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Llama Prompt Guard 2 86M cost?

Llama Prompt Guard 2 86M costs $0.04 per 1M input tokens and $0.04 per 1M output tokens on Groq.

### What is the context window of Llama Prompt Guard 2 86M?

Llama Prompt Guard 2 86M has a 512-token context window and returns up to 512 tokens per response.

### Which providers offer Llama Prompt Guard 2 86M?

Llama Prompt Guard 2 86M is available from Groq through LiteLLM, using the model name groq/meta-llama/llama-prompt-guard-2-86m.

### How do I call Llama Prompt Guard 2 86M with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="groq/meta-llama/llama-prompt-guard-2-86m", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### When did LiteLLM add Llama Prompt Guard 2 86M?

Llama Prompt Guard 2 86M was added to LiteLLM's model price file on August 13, 2026.

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