All models

Llama Guard 3 8B

MetaOpen weights131K context

Lowest price, from Nebius

Pricing page

Per million tokens

Input
$0.02
Output
$0.06
Cached input
—
Batch input / output
—
  • Up to 128K output tokens per request.

Estimate your monthly cost

Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.

From Nebius: $0.32 a month.

Where to buy it (4)

Sorted by your monthly estimate. Prices per million tokens.

  • NebiusCheapest

    Input / output
    $0.02 / $0.06
    Context
    128K
    Per month
    $0.32

    nebius/meta-llama/Llama-Guard-3-8B

  • DeepInfra

    Input / output
    $0.055 / $0.055
    Context
    131K
    Per month
    $0.66

    deepinfra/meta-llama/Llama-Guard-3-8B

  • Fireworks AI

    Input / output
    $0.20 / $0.20
    Context
    131K
    Per month
    $2.40

    fireworks_ai/accounts/fireworks/models/llama-guard-3-8b

  • Cloudflare Workers AI

    Input / output
    $0.484 / $0.03
    Context
    131K
    Per month
    $4.90

    cloudflare/@cf/meta/llama-guard-3-8b

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: —.

Similar models

About this data

Prices come from LiteLLM's model cost map (MIT licence), checked Oct 14, 2026; confirm on the seller's pricing page before you rely on a number.