NVIDIA: Nemotron 3 Super (free)
Nemotron 3 Super is a text-in, text-out model from NVIDIA with a 1-million-token context window and a maximum output of 262,144 tokens. It accepts tool calls and supports reasoning, making it usable for agentic workflows and multi-step problem decomposition. Structured output support is unconfirmed. The model is currently available at no cost on this platform. For comparison purposes, the free pricing makes it worth testing for high-volume or long-context tasks where cost is a barrier with other models. The significant caveat is that there is no independent benchmark coverage at this time, so its quality relative to scored alternatives is unverified. Developers and researchers who want to explore a long-context, tool-capable model without budget risk may reasonably shortlist it, but should plan their own evaluation rather than relying on published scores.
- Model ID
- nvidia/nemotron-3-super-120b-a12b:free
- Vendor
- nvidia
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 262,144 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no