# Meta Llama Prompt Guard 2 86M

> Meta Llama Prompt Guard 2 86M is a proprietary language model from Meta, released on 1 Oct 2024. It accepts text and generates text, with a 512-token context window and up to 2 output tokens per response. As of 21 Oct 2026, the lowest listed API price is $0.04 per million input tokens and $0.04 per million output tokens (Groq), across 1 provider we track.

Source page: https://www.aimodel.directory/models/llama-prompt-guard-2-86m
Last verified: 21 Oct 2026

## Specifications

- **Developer:** Meta
- **Release date:** 1 Oct 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/helicone/models/llama-prompt-guard-2-86m.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/helicone/models/llama-prompt-guard-2-86m.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/helicone/models/llama-prompt-guard-2-86m.toml)
- **Context window:** 512 (512 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/helicone/models/llama-prompt-guard-2-86m.toml)
- **Max output:** 2 tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/helicone/models/llama-prompt-guard-2-86m.toml)
- **Knowledge cutoff:** Oct 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/helicone/models/llama-prompt-guard-2-86m.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/helicone/models/llama-prompt-guard-2-86m.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/helicone/models/llama-prompt-guard-2-86m.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/helicone/models/llama-prompt-guard-2-86m.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/helicone/models/llama-prompt-guard-2-86m.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Groq | $0.04 | $0.04 | – | 512 |

## FAQ

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

Meta Llama Prompt Guard 2 86M has a context window of 512 tokens (512) and can generate up to 2 tokens in a single response, according to models.dev.

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

Meta Llama Prompt Guard 2 86M is listed from $0.04 per million input tokens and $0.04 per million output tokens (Groq). Prices last verified 21 Oct 2026.

### Is Meta Llama Prompt Guard 2 86M open source?

No. Meta Llama Prompt Guard 2 86M is a proprietary model; Meta has not released its weights. It is available through APIs including Groq.

### When was Meta Llama Prompt Guard 2 86M released?

Meta released Meta Llama Prompt Guard 2 86M on 1 Oct 2024, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Meta Llama Prompt Guard 2 86M", https://www.aimodel.directory/models/llama-prompt-guard-2-86m