Skip to content
llmprice

Llama 3.3 70B Versatile

Updated Sep 11, 2026

llama131k context33k max outputreleased Dec 6, 2024Open weightsTool calling
Cheapest input
$0.59
Cheapest output
$0.79
Official
output per 1M tokens
Providers
2
offering this model
Spread
1.0×
max / min output

Offers

Metered per-token prices. Cheapest input and output are highlighted; marks a context-tier surcharge.

Provider1M input1M output1M cache read1M cache writeContext
AbacusopenCheapest$0.59$0.79128k
Helicone$0.59Cheapest$0.79131k

Other llama models