LLM Reference
Microsoft Foundry

Using Prompt Guard 86M on Microsoft Foundry

Implementation guide · Prompt Guard · AI at Meta

ProvisionedOpen Weights

Microsoft Foundry exposes Prompt Guard 86M through model ID prompt-guard-86m. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-09. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Microsoft Foundry and generate an API key.
  2. 2
    Use the Microsoft Foundry SDK or REST API to call prompt-guard-86m — see the documentation for request format.
  3. 3
    You'll be billed $0.05/1M input, $0.05/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See Microsoft Foundry documentation for integration details.

Pricing on Microsoft Foundry

TypePrice (per 1M)
Input tokens$0.05
Output tokens$0.05

Capabilities

No model capability flags are currently sourced.

About Prompt Guard 86M

PromptGuard is a classifier model trained on a large corpus of attacks, which is capable of detecting both explicitly malicious prompts (Jailbreaks) as well as prompts that contain injected inputs (Prompt Injections).

Full model details →

Model Specs

Released2024-07-23
Parameters279M
Context512
ArchitectureDecoder Only

Provider

Microsoft Foundry
Microsoft Foundry

Microsoft

Redmond, Washington, United States