Groq · synced 2026-08-11

llama-3.3-70b-versatile

Input / 1M
$0.59
Output / 1M
$0.79
Cached input
Context
128K

A 1,000-token prompt costs $0.00059 to send. Token counts for Groq models are estimated — approximated, because this family has no public tokenizer.

Priced closest to this

Model Provider Input Output
llama3.1-70b Cerebras $0.60 $0.60
gpt-audio-mini OpenAI $0.60 $2.40
kimi-k2-0711-preview Moonshot $0.60 $2.50
kimi-k2-0905-preview Moonshot $0.60 $2.50 compare
kimi-k2-thinking Moonshot $0.60 $2.50
kimi-k2.5 Moonshot $0.60 $3.00 compare

Compare llama-3.3-70b-versatile