modelbenchmark.io

Llama 3.3 70B

Meta · llama-3-3-70b-versatile

Compare

Open Llama instruction model for multilingual chat, reasoning, and coding

Specification

most-agreed values

Context
131K
Max output
33K
Released
2024-12-06
Knowledge cutoff
2023-12
Retires
2026-08-16
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.59
Output
$0.79

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
abacus$0.59$0.79128K33K
groq$0.59$0.79131K33K2026-08-16
helicone$0.59$0.79131K33K

Other listings of this model

this page is one of them

The corpus files Llama 3.3 70B under several keys. This page is the llama-3-3-70b-versatile listing. The full record — every host, every price and every benchmark score — is on the main Llama 3.3 70B page.

More from Meta

most-hosted first