Questions? hello@viberation.devGet supportBlogDocsChangelog
Get started

Llama

Meta's open-weight family, and the reason local models took off.

Llama is Meta's open-weight family and the one that made running a serious model on your own hardware normal — most local tooling was built for it first, so support is everywhere. The Llama 4 models are mixture-of-experts and multimodal, with very large context windows, and the line includes Llama Guard, a classifier for filtering input and output rather than a chat model. Meta's newer work ships under a different name, so check the dates on this family before choosing it.

At a glance — Llama Guard 4 12B

Cost
$0.18 in · $0.18 out per 1M tokensBudget
Memory
164K tokens — about 250 pages
Reads
Text · Images
Can do
  • Use tools (agents) (not supported)
  • Structured output (not supported)
  • Thinking mode (not supported)
Reliability
100.00% uptime, last 24h
Released
Apr 30, 2025
Advanced details
API model ID
meta-llama/llama-guard-4-12b
Max output
16K tokens
Knowledge cutoff
2024-08-31
Tokenizer
Other

Providers

The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.

ProviderInput /1MOutput /1MCached /1MMax outputUptime 24h
DeepInfra · bf16$0.18$0.18—16K100.00%

Supported parameters

  • frequency_penalty
  • logit_bias
  • max_tokens
  • min_p
  • presence_penalty
  • repetition_penalty
  • seed
  • stop
  • temperature
  • top_k
  • top_p

Live from OpenRouter, refreshed hourly.

Key info

Pricing
Open source
Category
Models
Best for
Intermediate
Made by
Meta
Weights
Open
Good for
Local setups, where tooling support is widest

More in Models

  • France's frontier lab, with the small models everyone self-hosts.

    Models
  • Meta's current line, built for long multi-agent runs.

    Models
  • The open-weight family everyone else gets benchmarked against.

    Models
  • Google's open models — Gemini's research, small enough to self-host.

    Models