meta-llama

Meta Llama Guard 4 12B

meta-llama/llama-guard-4-12b

Input$0.180 /1M tokens
·
Output$0.180 /1M tokens

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

Code Examples

import requests

response = requests.post(
    "https://neurongate.net/v1/chat/completions",
    headers={
        "Authorization": "Bearer ng-your-api-key",
        "Content-Type": "application/json"
    },
    json={
        "model": "meta-llama/llama-guard-4-12b",
        "messages": [
            {"role": "user", "content": "Hello!"}
        ]
    }
)

print(response.json()["choices"][0]["message"]["content"])

Pricing Details

ExampleCost
1K input tokens (short prompt)$0.00018
1K in + 500 out (typical response)$0.00027
10K in + 2K out (document analysis)$0.00216
100K in + 10K out (large context)$0.0198

Prices in USD. Billed per actual token usage. Prepay with USDT, USDC, ETH, or BTC.

Frequently Asked Questions

Capabilities

Streaming
Yes
Function Calling / Tools
No
Vision (Image Input)
Yes
Audio Processing
No

Context Window

164K tokens

~123K words of text

Max output
16K tokens

Modalities

Input
imagetext
Output
text

Ready to build?

Pay with crypto. No subscriptions.

Get Started Free

Similar Models