impulse

Llama Guard 3 8B

Open weightsModeration
API id Llama-Guard-3-8B
Input / 1M
$0.02
at Nebius AI Studio
Output / 1M
$0.06
at Nebius AI Studio
Context window
128K
tokens
Max output
128K
tokens per reply
Hosts
4
4 listings
Released
-
date not published

Pricing

List prices at Nebius AI Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.02$0.06

What it costs a month

At Nebius AI Studio list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$10.50
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$11.76
  • Coding agent1,000 requests a day, 40K in / 2K out$27.60
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$62.40
Use your own numbers

Where to run it

4 hosts serve Llama Guard 3 8B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Llama-Guard-3-8B
$0.02 / $0.06
DeepInfraInference
Llama-Guard-3-8B
$0.055 / $0.055
+83% vs headline
Fireworks AIInference
llama-guard-3-8b
$0.20 / $0.20
+567% vs headline
llama-guard-3-8b
$0.484 / $0.03
+1135% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Llama Community License
Runtimes: Ollama, TGI, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Nebius AI Studio.

Smaller Meta models

No cheaper Meta model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

No cheaper open-weight match.

Model line

Newer and older versions, at each lab's own price.

  1. UndatedLlama Guard 3 8BLatest$0.02 / $0.06
  2. UndatedLlama Guard 2 8B$0.20 / $0.20

Call it

Using Nebius AI Studio's API.

Python
from litellm import completion

response = completion(
    model="nebius/Llama-Guard-3-8B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Llama Guard 3 8B cost?

On Nebius AI Studio, Llama Guard 3 8B costs $0.02 per million input tokens and $0.06 per million output tokens.

Which APIs offer Llama Guard 3 8B?

Llama Guard 3 8B runs on 4 APIs: Nebius AI Studio, DeepInfra, Fireworks AI and Cloudflare Workers AI.

What is Llama Guard 3 8B's context window?

128K tokens, with up to 128K tokens in one reply.

Is Llama Guard 3 8B being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Llama Guard 3 8B?

No. Llama Guard 3 8B is the newest model in its line.

What is Llama Guard 3 8B's API model id?

Use Llama-Guard-3-8B with Nebius AI Studio. Other hosts use their own ids: llama-guard-3-8b on Fireworks AI, llama-guard-3-8b on Cloudflare Workers AI.

Sources

Raw catalog entry for Llama-Guard-3-8B on Nebius AI Studio
{
  "max_input_tokens": 128000,
  "max_output_tokens": 128000,
  "input_cost_per_token": 2e-8,
  "output_cost_per_token": 6e-8,
  "litellm_provider": "nebius",
  "mode": "chat",
  "source": "https://nebius.com/prices"
}