# Llama Guard 3 8B

> Llama Guard 3 8B is an open-weight language model from Meta, released on 23 Jul 2024. It accepts text and generates text, with a 131K-token context window and up to 131K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.48 per million input tokens and $0.03 per million output tokens (Cloudflare Workers AI), across 1 provider we track.

Source page: https://www.aimodel.directory/models/llama-guard-3-8b
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Meta
- **Release date:** 23 Jul 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-guard-3-8b.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-guard-3-8b.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-guard-3-8b.toml)
- **Context window:** 131K (131,072 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-guard-3-8b.toml)
- **Max output:** 131K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-guard-3-8b.toml)
- **Knowledge cutoff:** Dec 2023 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-guard-3-8b.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-guard-3-8b.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-guard-3-8b.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-guard-3-8b.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-guard-3-8b.toml)
- **Structured output:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-guard-3-8b.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Cloudflare Workers AI | $0.48 | $0.03 | – | 131K |

## FAQ

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

Llama Guard 3 8B has a context window of 131,072 tokens (131K) and can generate up to 131,072 tokens in a single response, according to models.dev.

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

Llama Guard 3 8B is listed from $0.48 per million input tokens and $0.03 per million output tokens (Cloudflare Workers AI). Prices last verified 4 Oct 2026.

### Is Llama Guard 3 8B open source?

Llama Guard 3 8B is an open-weight model. Check the license terms before commercial use.

### When was Llama Guard 3 8B released?

Meta released Llama Guard 3 8B on 23 Jul 2024, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Llama Guard 3 8B", https://www.aimodel.directory/models/llama-guard-3-8b