impulse

Llama Prompt Guard 2 22M

Open weightsModeration
API id llama-prompt-guard-2-22m
Input / 1M
$0.03
at Groq
Output / 1M
$0.03
at Groq
Context window
512
tokens
Max output
512
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Groq, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.03$0.03

What it costs a month

At Groq list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$11.25
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$15.48
  • Coding agent1,000 requests a day, 40K in / 2K out$37.80
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$79.20
Use your own numbers

Where to run it

1 host serve Llama Prompt Guard 2 22M. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
GroqInference
llama-prompt-guard-2-22m
$0.03 / $0.03

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Llama Community License
Runtimes: Ollama, TGI, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Groq.

Smaller Meta models

No cheaper Meta model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

No cheaper open-weight match.

Call it

Using Groq's API.

Python
from litellm import completion

response = completion(
    model="groq/llama-prompt-guard-2-22m",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Llama Prompt Guard 2 22M cost?

On Groq, Llama Prompt Guard 2 22M costs $0.03 per million input tokens and $0.03 per million output tokens.

Which APIs offer Llama Prompt Guard 2 22M?

Llama Prompt Guard 2 22M runs on 1 API: Groq.

What is Llama Prompt Guard 2 22M's context window?

512 tokens, with up to 512 tokens in one reply.

Is Llama Prompt Guard 2 22M being retired?

No retirement date is scheduled for it on any API we track.

What is Llama Prompt Guard 2 22M's API model id?

Use llama-prompt-guard-2-22m with Groq.

Sources

Raw catalog entry for llama-prompt-guard-2-22m on Groq
{
  "input_cost_per_token": 3e-8,
  "litellm_provider": "groq",
  "max_input_tokens": 512,
  "max_output_tokens": 512,
  "mode": "chat",
  "output_cost_per_token": 3e-8,
  "source": "https://console.groq.com/docs/models"
}