InferIndex
Language, English, EN
Account

ModelsMetaLlama Guard 4 12B

Llama Guard 4 12B

meta-llama/llama-guard-4-12b164k context Compare →
Offers
10
Providers
3

Cheapest right now

DeepInfra

The provider's published policy: prompts are not used for training.

directYou buy access straight from the company that runs the model on its servers. · bf16 · 164k

$0.18 blended / 1M tokens

No change7D
in
$0.18
out
$0.18
Cached input
–
Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

Llama Guard 4 12B costs from $0.18 per million tokens (at a 3:1 input:output mix): the cheapest current offer, at DeepInfra, checked on ; 10 offers are listed.

Listed offers, by price

Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.

Offers not counted in cheapest, median or most expensive (9)

  • $0.18 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.18 · DeepInfra via Hugging Face · another route of the same provider
  • $0.18 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.18 · Glama via Glama · cannot be designated the cheapest
  • $0.18 · Martian via Martian · cannot be designated the cheapest
  • $0.18 · DeepInfra via OpenRouter · another route of the same provider
  • $0.27 · DeepInfra · priority tier
  • $0.27 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.27 · DeepInfra via OpenRouter · priority tier

Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.

Cheapest offer and official list price, by day, 30 days
DayCheapest offerOfficial list price
2026-10-02$0.18, DeepInfra–
2026-10-03$0.18, DeepInfra–
2026-10-04$0.18, DeepInfra–
2026-10-05$0.18, DeepInfra–
2026-10-06$0.18, DeepInfra–
2026-10-07$0.18, DeepInfra–
2026-10-08$0.18, DeepInfra–
2026-10-09$0.18, DeepInfra–
2026-10-10$0.18, DeepInfra–
2026-10-11$0.18, DeepInfra–
2026-10-12$0.18, DeepInfra–
2026-10-13$0.18, DeepInfra–
2026-10-14$0.18, DeepInfra–
2026-10-15$0.18, DeepInfra–
2026-10-16$0.18, DeepInfra–
2026-10-17$0.18, DeepInfra–
2026-10-18$0.18, DeepInfra–
2026-10-19$0.18, DeepInfra–
2026-10-20$0.18, DeepInfra–
2026-10-21$0.18, DeepInfra–
2026-10-22$0.18, DeepInfra–
2026-10-23$0.18, DeepInfra–
2026-10-24$0.18, DeepInfra–
2026-10-25$0.18, DeepInfra–
2026-10-26$0.18, DeepInfra–
2026-10-27$0.18, DeepInfra–
2026-10-28$0.18, DeepInfra–
2026-10-29$0.18, DeepInfra–
2026-10-30$0.18, DeepInfra–
2026-10-31$0.18, DeepInfra–

Cheapest offer

Offers

10 of 10 offers

Offers for Llama Guard 4 12B, one row per offer, sorted by blended price.
RankProvider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.Input $/1MOutput $/1MBlended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.SignalsOffer
1 DeepInfra 0.18 0.18 0.18 bf16 164k United States
Go to offer at DeepInfra (opens in a new tab)
2 DeepInfravia Eden AI 0.18 0.18 0.18 bf16 164k United States Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
3 DeepInfravia Hugging Face 0.18 0.18 0.18 bf16 164k United States
See pricing at Hugging Face (opens in a new tab)
4 DeepInfravia Kilo Gateway 0.18 0.18 0.18 bf16 164k United States Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
5 Glama 0.18 0.18 0.18 – 164k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
6 Martian 0.18 0.18 0.18 – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Martian (opens in a new tab)
7 DeepInfravia OpenRouter 0.18 0.18 0.18 bf16 164k United States Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
8 DeepInfra 0.27 0.27 0.27 bf16 164k United States Priority tier: A different service tier, with its own speed and availability conditions.
Go to offer at DeepInfra (opens in a new tab)
9 DeepInfravia Kilo Gateway 0.27 0.27 0.27 bf16 164k United States Unverified. No public page for this offer: listed, not designated cheapestPriority tier: A different service tier, with its own speed and availability conditions.
: Kilo Gateway (opens in a new tab). No public price page for this model
10 DeepInfravia OpenRouter 0.27 0.27 0.27 bf16 164k United States Priority tier: A different service tier, with its own speed and availability conditions.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)

No training on promptsPrompts may be used for trainingTraining terms not published

backend not named. The router bills this price itself without naming who serves the model.

  • DeepInfra

    $0.18

    direct

    in
    $0.18
    out
    $0.18
    Precision
    bf16
    Context
    164k

    No training on promptsUnited States

    Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

  • DeepInfra

    $0.18

    Eden AI

    in
    $0.18
    out
    $0.18
    Precision
    bf16
    Context
    164k

    Prompts may be used for trainingUnited StatesUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model

  • DeepInfra

    $0.18

    Hugging Face

    in
    $0.18
    out
    $0.18
    Precision
    bf16
    Context
    164k

    No training on promptsUnited States

    See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face

  • DeepInfra

    $0.18

    Kilo Gateway

    in
    $0.18
    out
    $0.18
    Precision
    bf16
    Context
    164k

    Training terms not publishedUnited StatesUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • Glama

    $0.18

    Glama

    in
    $0.18
    out
    $0.18
    Precision
    –
    Context
    164k

    No training on promptsUnverified. No public page for this offer: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    Seller's site: Glama (opens in a new tab)No public price page for this model

  • Martian

    $0.18

    Martian

    in
    $0.18
    out
    $0.18
    Precision
    –
    Context
    –

    Training terms not publishedworldwideUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    See pricing See pricing at Martian (opens in a new tab)via Martian

  • DeepInfra

    $0.18

    OpenRouter

    in
    $0.18
    out
    $0.18
    Precision
    bf16
    Context
    164k

    No training on promptsUnited StatesFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • DeepInfra

    $0.27

    direct

    in
    $0.27
    out
    $0.27
    Precision
    bf16
    Context
    164k

    No training on promptsUnited StatesPriority tier: A different service tier, with its own speed and availability conditions.

    Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

  • DeepInfra

    $0.27

    Kilo Gateway

    in
    $0.27
    out
    $0.27
    Precision
    bf16
    Context
    164k

    Training terms not publishedUnited StatesUnverified. No public page for this offer: listed, not designated cheapestPriority tier: A different service tier, with its own speed and availability conditions.

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • DeepInfra

    $0.27

    OpenRouter

    in
    $0.27
    out
    $0.27
    Precision
    bf16
    Context
    164k

    No training on promptsUnited StatesPriority tier: A different service tier, with its own speed and availability conditions.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at OpenRouter (opens in a new tab)via OpenRouter

3 flex or batch offers hidden (lower priority, variable latency).

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method

Monthly cost for your workload

Computed by the API for the three cheapest offers, per 30-day month.
  1. DeepInfra$13.50per month
  2. DeepInfra$20.25per month+$6.75 vs the cheapest

Host it yourself instead? See the break-even

Compare Llama Guard 4 12B with

Related models

More from Meta

All Meta models

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=meta-llama/llama-guard-4-12b
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

Also works in Cursor and Codex: see the MCP page.