Model Terminal

GPT OSS 20B

GPT OSS 20B is an open-weight, text-only reasoning model from OpenAI with approximately 21B total parameters and 3.6B active parameters per token via mixture-of-experts architecture, released under Apache 2.0. It supports tool use, structured outputs, and agentic workflows with a 128k context window, designed for local or edge deployment on consumer hardware. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Peer value bars

Identity

Developer
Hugging Face
Openness
Modalities
Text-generation
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed