Home / Models / Meta / Llama Guard 4 12B

Llama Guard 4 12B pricing and routing profile

Llama Guard 4 12B from Meta lists at $0.18 per million input tokens and $0.18 per million output tokens, with a 163,840-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.18
Output, per 1M tokens$0.18
Context window164K
Confidence signalNot exposed

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.11
Chat reply (2,000 in, 400 out)$0.432
Retrieval-augmented answer (8,000 in, 500 out)$1.53

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for Llama Guard 4 12B. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Cheaper models that can answer first

Models priced below Llama Guard 4 12B that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
Qwen3.5-9B$0.10 / $0.1540%
Llama 3.1 8B Instruct$0.05 / $0.0869%
Qwen3.7 Flash$0.03 / $0.1374%
Granite 4.0 Micro$0.017 / $0.11282%
gpt-oss-20b$0.018 / $0.0983%
Ling 3.0 Flash$0.021 / $0.06384%

Questions

How much does Llama Guard 4 12B cost?

Llama Guard 4 12B lists at $0.18 per million input tokens and $0.18 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.432 per 1,000 requests.

What is the context window of Llama Guard 4 12B?

163,840 tokens.

Can a cheaper model replace Llama Guard 4 12B?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Llama Guard 4 12B on one half of your requests and make at most three answers worse on the other.