[Meta] Llama 3.3 · 70B Versatile

deprecated

Meta Llama 3.3 (70B params) with GQA. Strong reasoning, coding, multilingual. 131K context, 32K max output. ~280 t/s on Groq. Retiring 2026-08-16 -> GPT-OSS 120B or Qwen3.6 27B.

131K context·$0.59 in·$0.79 out·Dec 2024 release·Tools / functions

Available on

Groq

Providers

Where [Meta] Llama 3.3 · 70B Versatile runs in Big-AGI, with each service's own model ID and USD-per-1M-token rates. The summary above prefers the creator's claim; rates below are each service's own.

ServiceModel IDContextInputOutput

Groq

delisted

llama-3.3-70b-versatile

131K

$0.59

$0.79

Specs as reported by each service · usage over the last 2 days · refreshed hourly