What is the context window of meta/llama-guard-3-8b?

meta/llama-guard-3-8b accepts up to 131,072 tokens (131K) of context per request.

How much does meta/llama-guard-3-8b cost per million tokens?

Through Wide Area Intelligence, meta/llama-guard-3-8b costs $0.53 per 1M input tokens and $0.033 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $0.57.

Can I run meta/llama-guard-3-8b on my own hardware?

Yes — meta/llama-guard-3-8b is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 5.3 GB of GPU memory, plus room for the context cache — it fits a single 8 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

← model directory

cloudflare

meta/llama-guard-3-8b

Name: meta/llama-guard-3-8b
Brand: cloudflare
Price: 0.5324 USD

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

↓ runs free on your own hardware⚙ tool calling

Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.

specs & pricing

Type: text
Provider: cloudflare
Model ID: cloudflare/meta/llama-guard-3-8b
Capabilities: tools
Context window: 131K tokens
Self-hostable: Yes — runs on your own GPU
Input price: $0.53 / 1M tokens
Output price: $0.033 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$0.57

$0.53 for a million input tokens plus $0.033 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

$0 / token

Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.

AI cost calculator →GPU power cost →

Run it on your own hardware

Estimated GPU memory for meta/llama-guard-3-8b (8.0B parameters), for the weights alone — add room for the context cache.

Q4_K_M: ~5.3 GBfits a 8 GB card
Q8_0: ~8.6 GBfits a 12 GB card
FP16 / BF16: ~15.7 GBfits a 16 GB card

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

VRAM calculator →Which GPU do I need? →

/// initialize

Call meta/llama-guard-3-8b through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

Run it on your own hardware Try it in chat

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of meta/llama-guard-3-8b?: meta/llama-guard-3-8b accepts up to 131,072 tokens (131K) of context per request.
How much does meta/llama-guard-3-8b cost per million tokens?: Through Wide Area Intelligence, meta/llama-guard-3-8b costs $0.53 per 1M input tokens and $0.033 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $0.57.
Can I run meta/llama-guard-3-8b on my own hardware?: Yes — meta/llama-guard-3-8b is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 5.3 GB of GPU memory, plus room for the context cache — it fits a single 8 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from cloudflare

← browse all models