Llama Guard 4 12B

Open weights

Llama Guard 4 12B is a language model from Meta with a 1M-token context window. Provider list price is $0.20 per million input tokens and $0.20 per million output; on Allocate you pay $0.21 and $0.21 with the 7% transaction fee. The weights are open under Llama community, so you can fine-tune it and own the result.

Route Llama Guard 4 12B Talk to sales

Pricing

Provider listOn Allocate

Input, per M tokens$0.20$0.21

Output, per M tokens$0.20$0.21

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

Price against its peers

Mistral Small (24B) Instruct 25.01$0.10$0.30

Llama Guard 4 12B$0.20$0.20

Meta Llama 3 8B Instruct Reference$0.20$0.20

Meta Llama 3 8B Instruct$0.20$0.20

Meta Llama 3.1 8B$0.20$0.20

Ministral 3 14B Instruct 2512$0.20$0.20

Mistral (7B) Instruct v0.1$0.20$0.20

Mistral (7B) Instruct v0.3$0.20$0.20

InputOutput

Provider list prices per M tokens, Llama Guard 4 12B against its nearest language peers by price.

What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0.20 + 350 × $0.20 = $310 a month. Billed on Allocate it is $331.70 with the 7% transaction fee.

Llama Guard 4 12B is an open-weights model under the Llama community license. Read the license terms once before you build on it; fine-tuned weights on Allocate stay inside your boundary.

Example usage

Point a route at meta/llama-guard-4-12b and the endpoint never changes; swap the model behind it whenever you want.

api.allocate.network

curl https://api.allocate.network/v1/chat/completions \
  -H "Authorization: Bearer $ALLOCATE_KEY" \
  -d '{
    "model": "meta/llama-guard-4-12b",
    "messages": [{"role": "user",
      "content": "Summarise the attached contract."}]
  }'

200 · meta/llama-guard-4-12b · inside your boundary

Common questions

How much does Llama Guard 4 12B cost per million tokens?

Provider list price is $0.20 per million input tokens and $0.20 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $0.21 in and $0.21 out.

What context window does Llama Guard 4 12B have?

1,048,576 tokens (1M). At roughly 0.75 words per token, that is about 786k words of English text per request.

Can I fine-tune Llama Guard 4 12B?

Yes. Llama Guard 4 12B is an open-weights model under the Llama community license. Read the license terms before fine-tuning for commercial use. On Allocate the trained weights stay inside your boundary and belong to you.

How do I call Llama Guard 4 12B on Allocate?

Send meta/llama-guard-4-12b in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.