Llama Guard 3 8B

Provider: Meta Llama US

No longer listed on OpenRouter since 2026-06-12. The figures below are the last recorded values.
Input price
$0.48
/ 1M tokens
Output price
$0.03
/ 1M tokens
Context
131K tokens
Max output 131K tokens

Overview

Llama Guard 3 8B is a model offered by Meta Llama (US) with an impressive 131,072 token context window and equal maximum output length. Its specific capabilities are listed as unknown, which limits precise determination of its intended tier or target workloads.

Strengths

  • Large 131,072 token context window supports extensive input processing.
  • Equal 131,072 token maximum output ensures comprehensive response generation.
  • Exceptionally low output pricing at $0.03 per million tokens.

Best use cases

  • Handling extensive documents or conversations due to its large context window.
  • Scenarios requiring generation of significant output efficiently given the low output price.
  • Applications benefiting from a consistent 131,072 token context for both input and output.

Pricing position

This model features an input price of $0.484 per million tokens, positioning it similarly to peers like Gemini 3 Flash Preview ($0.5/M) and Mistral Large 3 2512 ($0.5/M). However, its output price is an exceptionally low $0.03 per million tokens, significantly undercutting all listed peers which range from $1.50/M to $3.00/M. Compared to other Meta Llama 8B Instruct models, Llama Guard 3 8B is considerably more expensive for input but offers a lower output cost.

Caveats

The primary limitation is that its specific capabilities are listed as unknown, making it difficult to determine its suitability for specialized tasks like reasoning or vision. Its input price of $0.484/M is substantially higher than other Llama 8B Instruct models, meaning a cheaper sibling might be more cost-effective if its unique (but unknown) features are not essential. There is also no free tier available for testing or low-volume use.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Max output
131K tokens
Tracked since
2026-05-08
Last updated
2026-06-12

Features

No information available

Price history

  • 2026-06-12 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.05
1M (small app) 1 0.5 $0.50
10M (mid scale) 10 5 $4.99
100M (large) 100 50 $49.90

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Meta Llama

Similar-priced models

Source: OpenRouter API