modelbenchmark.io

OpenAI GPT-oss-120b

openai-gpt-oss-120b

Compare

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Specification

most-agreed values

Context
128K
Max output
4K
Released
2025-08-05
Knowledge cutoff
2024-06
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.055
Output
$0.385
Cache read
$0.02

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
digitalocean$0.055$0.385$0.02128K4K
venice$0.07$0.30128K16K