Skip to content
Rapid Router
← All models

Llama-Guard-3-8B (Deep Infra)

meta-llama/llama-guard-3-8b

Meta model · Served by DeepInfra · live on the gateway · :free available

Input / 1M
$0.055
Output / 1M
$0.055
Context
131K tokens
Max output
4K tokens
Input
Text
Released
2y ago

Pricing

Input tokens$0.055 per 1M
Output tokens$0.055 per 1M
Provider list priceExactly what your balance is debited; our fee is charged when you buy credits

About Llama-Guard-3-8B (Deep Infra)

Llama 3.1-based safety classifier for moderating prompts and model responses

What it supports

  • Tool calling (function calling)
  • JSON mode and structured output
  • Image input (vision)
  • Audio input
  • Extended reasoning
  • Streaming responses
  • OpenAI SDK, Anthropic SDK and any OpenAI-compatible client

Make a request

curl https://rapidrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $RAPIDROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-guard-3-8b",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Frequently asked

How do I call Llama-Guard-3-8B (Deep Infra) through an OpenAI-compatible API?

Point any OpenAI-compatible client at https://rapidrouter.ai/api/v1 with a Rapid Router API key and set the model to meta-llama/llama-guard-3-8b. The chat completions endpoint is https://rapidrouter.ai/api/v1/chat/completions.

What is the context window of Llama-Guard-3-8B (Deep Infra)?

Llama-Guard-3-8B (Deep Infra) has a context window of 131,072 tokens on Rapid Router, and returns up to 4,096 output tokens per reply.

Is there a free version of Llama-Guard-3-8B (Deep Infra)?

Yes. Call meta-llama/llama-guard-3-8b:free and the request is paid for from Rapid Router's sponsored daily pool, within the free tier's daily request limit.

More Llama models