Prompt Guard 86M

Overall 41Open weightopen-weight

Meta's lightweight 86M Prompt Guard for detecting jailbreak and prompt injection attempts.

Last verified: 2026-03-29Confidence: MediumSources: 2

textvisionopen-source

Input price

Not applicable

Output price

Not applicable

Context window

512

Max output

512

Release date

2024-07-23

Access

open-weight, self-hosted, hosted

License

Llama Community License

Last verified

2026-03-29

Capability profile

Radar view of the model's practical strengths. This chart is backed by textual summaries below for crawlability.

Benchmark summary

This entry has source-backed metadata, but benchmark coverage is still sparse, so the page emphasizes published specs and deployment fit.

No benchmark series is attached to this model yet. Source links and product metadata are available below.

Strengths

• Source-backed listing for safety buyers
• Useful when deeper benchmark profiling is still incomplete

Trade-offs

• Detailed benchmark coverage is still limited for this entry
• Some pricing or capability fields may remain unpublished

Crawlable benchmark analysis

Prompt Guard 86M is positioned as a safety model with published scores that emphasize its practical fit for buyers evaluating the entry.

Published scores highlight reasoning 20/100, coding 5/100, enterprise readiness 60/100, vision 10/100, speed 99/100, and safety 85/100.

Pricing is not applicable for this self-hosted or open-weight entry. With a context window of 512 tokens, it supports large-document analysis and retrieval workflows.

Benchmark coverage is still limited for this entry, so this section focuses on published metadata and deployment fit.

Sources

Provider and distribution links used to verify this model record.

Last verified: 2026-03-29

Meta Llama website
official-website
Open link
Llama docs
official-docs
Open link

Related models

OpenAI

GPT-5.4

OpenAI

OpenAI's GPT-5.4, the most capable and efficient frontier model for professional work. First general-purpose model with native computer-use capabilities. Combines industry-leading coding from GPT-5.3-Codex with improved agentic workflows.

Score 933 sources

textreasoningtool-usevisionapihosted

Context: 1,000,000
Input: $0.005/1K tok
Output: $0.02/1K tok
Coverage: Full profile

View analysis

Anthropic

Claude Sonnet 4.6

Claude 4.6

Anthropic's current Sonnet tier for fast frontier reasoning, coding, and long-context agent work.

Score 923 sources

textvisionreasoningcodetool-useapihosted

Context: 1,000,000
Input: $0.003/1K tok
Output: $0.02/1K tok
Coverage: Full profile

View analysis

Anthropic

Claude Opus 4.6

Claude 1M

Anthropic's most intelligent Claude model for complex agents, coding, and deep reasoning, with 1M token context and 128K output.

Score 913 sources

textvisionreasoningapihosted

Context: 1,000,000
Input: $0.005/1K tok
Output: $0.03/1K tok
Coverage: Full profile

View analysis