Cracked AI Engineering

GPT OSS 120B vs Qwen 3 235B Instruct

GPT OSS 120B includes advanced reasoning. Compare full specs, pricing, and choose the best model for your use case.

Quick Overview

GPT OSS 120B

Cerebras

131K tokens context • $0.25 / $0.69 per 1M tokens

View full specifications →

Qwen 3 235B Instruct

Cerebras

131K tokens context • $0.60 / $1.20 per 1M tokens

View full specifications →

Detailed Comparison

Specification
GPT OSS 120B
Qwen 3 235B Instruct
Provider
Cerebras
Cerebras
Context Window
131K tokens
131K tokens
Max Output Tokens
33K tokens
32K tokens
Input Pricing (per 1M tokens)
$0.25
$0.60
Output Pricing (per 1M tokens)
$0.69
$1.20
Release Date
Aug 2025
Jul 2025

Capabilities

Capability
GPT OSS 120B
Qwen 3 235B Instruct
Text Generation
Function Calling
Advanced Reasoning

Which Model Should You Choose?

Choose GPT OSS 120B if:

  • • You need a larger context window
  • • Cost efficiency is a priority
  • • You need advanced reasoning

Choose Qwen 3 235B Instruct if: