Fresh paint, wet floors — we're rebuilding CostOfToken into a cross-provider price comparison. Some corners are still under construction; the full version is coming up soon.

meta-llama/Llama-Guard-4-12B pricing

Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification. meta-llama/Llama-Guard-4-12B from DeepInfra costs $0.180 per 1M input tokens and $0.180 per 1M output tokens. Context window 163,840 tokens.

API id meta-llama/Llama-Guard-4-12B · DeepInfra · source · updated 2026-09-25

We have not confirmed what kind of model this is. Its name suggests one thing and its pricing another, and we would rather say so than guess.

$0.180
Input / 1M tokens
$0.180
Output / 1M tokens
—
Cached input / 1M
164K
Context window

meta-llama/Llama-Guard-4-12B specifications

Provider
DeepInfra
API id
meta-llama/Llama-Guard-4-12B
Model type
unknown
Context window
164K tokens
Max output
not published
Currency
USD
Price source
Provider API
Last checked
2026-09-25

Meta: Llama Guard 4 12B across providers

The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.

ProviderInput /1MCached /1MOutput /1M1M in + 1M outvs vendor
DeepInfraHostCheapestviewing
$0.180—$0.180$0.36—
$0.180—$0.180$0.36—

What meta-llama/Llama-Guard-4-12B costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0003
Document summary50,0002,000$0.0094
1M tokens in, 200K out1,000,000200,000$0.22

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Common questions

How much does meta-llama/Llama-Guard-4-12B cost per 1M tokens?
meta-llama/Llama-Guard-4-12B costs $0.180 per 1M input tokens and $0.180 per 1M output tokens on the standard tier.
What is meta-llama/Llama-Guard-4-12B's context window?
meta-llama/Llama-Guard-4-12B accepts up to 163,840 tokens in a single request.
Is there a cheaper DeepInfra model than meta-llama/Llama-Guard-4-12B?
Yes. deepseek-ai/DeepSeek-V4-Flash is $0.090 per 1M input tokens versus $0.180 for meta-llama/Llama-Guard-4-12B, with a 1,048,576 token context window.
Where does this meta-llama/Llama-Guard-4-12B price come from?
From the OpenRouter catalogue, because DeepInfra does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepInfra's own — verify before committing spend.

Head-to-head comparisons

Other DeepInfra models

See all DeepInfra pricing →