Prompt Guard 2 86M pricing & specs
Meta · released 2025-04-29 · ● verified 2026-11-21 · beta
Prompt Guard 2 86M is a Meta model released on 2025-04-29. At $0.04 per million input tokens and $0.04 per million output tokens, its blended price of $0.04 per 1M tokens is lower than 98% of the 186 models we track. It offers text input, a 512-token context window. Its weights are open, and it is available from 1 tracked hosting providers.
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Prompt Guard 2 86M |
|---|---|---|---|---|
| Llama 3.2 1B Instruct (instruct) | $0.02 | $0.02 | 131K | −50% |
| Llama-3.1-8B-Instruct | $0.02 | $0.05 | 16.4K | −31.2% |
| DeepSeek OCR 2 | $0.03 | $0.03 | 8.2K | −25% |
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | +25% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | +37.5% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Groq | $0.04 | $0.04 |
// embed this price badge
Show the live price of Prompt Guard 2 86M in your README or docs (updated daily):
[](https://aisignals.dev/models/meta/llama-prompt-guard-2-86m)
// faq
How much does Prompt Guard 2 86M cost?
Prompt Guard 2 86M costs $0.04 per million input tokens and $0.04 per million output tokens (cheapest tracked host: Groq). At 50M input and 10M output tokens per month that is about $2.40.
What is the context window of Prompt Guard 2 86M?
512 tokens, with up to 512 output tokens per request.
What are cheaper alternatives to Prompt Guard 2 86M?
Llama 3.2 1B Instruct (instruct) ($0.02 in / $0.02 out), Llama-3.1-8B-Instruct ($0.02 in / $0.05 out), DeepSeek OCR 2 ($0.03 in / $0.03 out) offer the same input types and capabilities for less.
Is Prompt Guard 2 86M open weights?
Yes. It is available from 1 tracked hosts; the cheapest is Groq at $0.04 input and $0.04 output per million tokens.
// spec sheet
- input / 1M
- $0.04
- output / 1M
- $0.04
- blended (3:1)
- $0.04
- context
- 512
- max output
- 512
- input types
- text
- reasoning
- no
- tool calling
- no
- structured output
- no
- open weights
- yes
- knowledge cutoff
- n/a
- price source
- Groq
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Llama 3.2 1B Instruct (instruct) | $0.02 | $0.02 | $1.20 |
| Llama-3.1-8B-Instruct | $0.02 | $0.05 | $1.50 |
| DeepSeek OCR 2 | $0.03 | $0.03 | $1.80 |
| Prompt Guard 2 86M | $0.04 | $0.04 | $2.40 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.