Compare two models

Put any two models head to head. The cheaper price — or larger context — wins each row.

I/O price /1M

$2.50/$10.00

$5.00/$30.00

Input /1M

$2.50

$5.00

Output /1M

$10.00

$30.00

Cached in /1M

—

$0.5

I/O avg /1M

$4.38

$11.25

Context

128K

Δ since launch

27.1%

—

Tier

Frontier

Released

Apr 2024

Apr 2026

Status

legacy

—

Provider

C Cohere

OpenAI