NVIDIA: Nemotron Nano 9B V2 (free)

NVIDIA Nemotron Nano 9B V2 is a text-in, text-out model with a 128,000-token context window. It supports tool use and reasoning, which means it can handle multi-step tasks and agentic workflows. Structured output support is unconfirmed from available specifications, so teams with strict schema requirements should verify that before committing. No information is available on a maximum completion length, which is worth testing against your specific workload. The model is free to use, making it a low-risk option for developers who want to experiment with reasoning-capable models without incurring costs. The tradeoff is transparency: there is no independent benchmark coverage to compare it against other models in the same tier. Shortlist it if your priority is cost-free access to tool and reasoning support, but treat performance as unproven until you run your own evals against whatever you are currently using.