tokenstat
tokenstat

Meta: Llama Guard 3 8B

meta-llama/Llama-Guard-3-8B · rates as of · Benchmarks · Plans · Calculator

Safety model for policy screening, moderation, and risk-aware routing workflows

Cheapest input
$0.02
$/MTok · LiteLLM
Cheapest output
$0.06
$/MTok
Context
131K
tokens
Offers
11
2 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
LiteLLMcheapestnebius/meta-llama/Llama-Guard-3-8B$0.02$0.06$0.002
LiteLLMmeta-llama/Llama-Guard-3-8B$0.055$0.055$0.0055
LiteLLMLlama-Guard-3-8B$0.055$0.055$0.0055
LiteLLMdeepinfra/meta-llama/Llama-Guard-3-8B$0.055$0.055$0.0055
LiteLLMaccounts/fireworks/models/llama-guard-3-8b$0.2$0.2$0.02
LiteLLMfireworks_ai/accounts/fireworks/models/llama-guard-3-8b$0.2$0.2$0.02
models.devworkers-ai/@cf/meta/llama-guard-3-8bCloudflare$0.48$0.03$0128K
models.dev@cf/meta/llama-guard-3-8bCloudflare$0.484$0.03$0131K
LiteLLM@cf/meta/llama-guard-3-8b$0.484$0.03$0.0484
LiteLLMllama-guard-3-8b$0.484$0.03$0.0484
LiteLLMcloudflare/@cf/meta/llama-guard-3-8b$0.484$0.03$0.0484

Capabilities

  • Open weights
  • In: text
  • Out: text
Released: 2025-04-03Family: llama

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash