# Llama Guard 3 8B API Pricing

As of October 10, 2026, Llama Guard 3 8B costs $0.055 per 1M input tokens and $0.055 per 1M output tokens from DeepInfra, the lowest of 5 providers. It has a 131,072-token context window and returns up to 131,072 tokens per response.

- Page: https://models.litellm.ai/models/llama-guard-3-8b
- Lab: Meta
- LiteLLM model name: `deepinfra/meta-llama/Llama-Guard-3-8B`
- Context window: 131,072 tokens
- Max output: 131,072 tokens
- Added to LiteLLM: May 2025
- 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 |
|---|---|---|---|---|---|---|---|
| DeepInfra | `deepinfra/meta-llama/Llama-Guard-3-8B` | $0.055 | $0.055 | – | – | – | 128K |
| Cloudflare Workers AI | `cloudflare/@cf/meta/llama-guard-3-8b` | $0.484 | $0.03 | – | – | – | 128K |
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/llama-guard-3-8b` | $0.20 | $0.20 | – | – | – | 128K |
| Groq | `groq/llama-guard-3-8b` | $0.20 | $0.20 | – | – | – | 8K |
| Nebius AI Studio † | `nebius/meta-llama/Llama-Guard-3-8B` | $0.02 | $0.06 | – | – | – | 128K |

† Differs from other providers by more than 8x; check the provider's pricing page.

## Cost examples

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

- DeepInfra: $0.1375
- Fireworks AI: $0.50
- Groq: $0.50
- Cloudflare Workers AI: $0.983

100 long-document requests with 100,000 input and 2,000 output tokens each:

- DeepInfra: $0.561
- Fireworks AI: $2.04
- Groq: $2.04
- Cloudflare Workers AI: $4.846

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="deepinfra/meta-llama/Llama-Guard-3-8B",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Llama Guard 3 8B cost?

Llama Guard 3 8B costs $0.055 per 1M input tokens and $0.055 per 1M output tokens from DeepInfra, the lowest of 5 providers.

### What is the context window of Llama Guard 3 8B?

Llama Guard 3 8B has a 131,072-token context window and returns up to 131,072 tokens per response.

### Which providers offer Llama Guard 3 8B?

Llama Guard 3 8B is available from 5 providers through LiteLLM: DeepInfra, Cloudflare Workers AI, Fireworks AI, Groq and Nebius AI Studio. The lowest price is on DeepInfra.

### How do I call Llama Guard 3 8B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="deepinfra/meta-llama/Llama-Guard-3-8B", 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 Guard 3 8B?

Llama Guard 3 8B was added to LiteLLM's model price file in May 2025.

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