← Model Library

SCX AI · OpenAI-Compatible Engines

GPT OSS 120B

Language Reasoning Tool use

OpenAI's 117B open-weight MoE (5.1B active) achieving near o4-mini reasoning. 128k context, 128k max output.

Specifications

Parameters
117B total · 5.1B active
Architecture
Open-weight MoE
Context window
128K tokens
Max output
128K tokens
Licence
Apache-2.0

Best suited for

A capable all-rounder — the sensible default for everyday assistant and agent work.

General assistants Drafting & summarising Everyday agent tasks Step-by-step reasoning Tool use & function calling

Pricing (per million tokens)

Free

No per-token charge at present. Providers can change pricing — this page tracks the published rate.

Price history (USD per 1M tokens)

▮ cheaper ▮ pricier wick = input rate
$0 $0.3 $0.6 5 Aug 2025: $0.15 input / $0.6 output 1 Feb 2026: $0.037 input / $0.1 output 5 Aug 2025 1 Feb 2026

Input rate has fallen -75.3% since 5 Aug 2025.

Model id: gpt-oss-120b

The platform default — used automatically when no other provider is connected.

View all model pricing →

One Gateway, Every Model

Get an API key and point your first request at ApiSpi in minutes

Start Free Week Explore the LLM Gateway