← All models

gpt-oss 120B

Apache 2.0Planned

openai/gpt-oss-120b

Open-weight MoE with 5.1B active parameters. The best quality-per-dollar on the board — a single A100 serves it at MXFP4, which is where the undercut room is.

This model is on the roadmap but is not being served yet, so it will return model_not_found from the API. It appears here because we publish what we intend to run as openly as what we already do — the catalogue should tell you where the platform is going, not just where it is.