Compare two models

Select any two models. Input, output, cached, and context rarely move together — the cheaper model on one line isn't always the cheaper one on the next.

Description

A 70-billion-parameter instruction-tuned language model from Meta with a 131,072-token context window, released in December 2024.

OpenAI's frontier model for complex professional workloads. 1M token context, text + image input, native computer use.

I/O price /1M

$0.1/$0.32

$5.00/$30.00

Input /1M

$0.1

$5.00

Output /1M

$0.32

$30.00

Cached in /1M

—

$0.5

Context

131K

Δ input since launch

0.0%

—

Δ output since launch

0.0%

—

Released

Dec 2024

Apr 2026

Status

—

Provider