Prompt Guard 86M
Prompt Guard 86M is worth evaluating for classification when its provider route and context window match the workload.
Use it for
- Teams evaluating classification
- Workloads that can use a 512 context window
- Buyers comparing 1 tracked provider route
Do not use it for
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
- Family
- Prompt Guard
- Released
- 2024-07-23
- Context
- 512
- Parameters
- 279M
- Architecture
- Decoder Only
- Specialization
- safety
- Openness
- Open weights
- License
- Llama 3 CommunityCommercial use: conditional
- Weights
- Unknown
- Code
- Unknown
- Training
- Fine-tuned
Large-scale open-source AI for social technologies.
Cheapest of 1 route · Microsoft Foundry
About
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).
Prompt Guard 86M is an open-weight model in the Prompt Guard family. The structured metadata tracks a 512-token context window. This page tracks provider routes through Microsoft Foundry, with the cheapest tracked route listed at $0.05 input and $0.05 output per 1M tokens. No headline benchmark score is tracked for Prompt Guard 86M yet.
Top use-case fit
Classification
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Microsoft Foundry | $0.050 | $0.050 | Provisioned |
Available via routers & gateways(5)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
Azure AI Foundry Model Router
RouterMicrosoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Kong AI Gateway
GatewayMulti-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Classification
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
Frequently asked questions
What is the context window of Prompt Guard 86M?
Prompt Guard 86M has a context window of 512 tokens.
How much does Prompt Guard 86M cost?
Prompt Guard 86M is available at $0.05/1M input tokens through Microsoft Foundry.
When was Prompt Guard 86M released?
Prompt Guard 86M was released on 2024-07-23.
Which providers offer Prompt Guard 86M?
Prompt Guard 86M is available from 1 provider: Microsoft Foundry.
Large-scale open-source AI for social technologies.
Cheapest of 1 route · Microsoft Foundry