OpenAI: gpt-oss-120b (free)

GPT-OSS-120B (free) is a text-in, text-out model from OpenAI with a 131,072-token context window that covers both input and output. It supports tool use and reasoning, which makes it applicable to agentic workflows and multi-step tasks. Structured output support is unconfirmed, so developers who depend on that capability should verify before building around it. The case for shortlisting this model rests almost entirely on its price: zero cost for both input and output tokens. That makes it worth testing for high-volume or experimental use where budget is the primary constraint. The tradeoff is uncertainty about quality; there is no independent benchmark coverage to consult, so you would be evaluating it blind relative to scored alternatives. Teams with the capacity to run their own evals will get the most out of it, while anyone needing a validated quality baseline should look elsewhere first.