Nemotron Super
nvidia/nemotron-superFree, open reasoning engineered for maximum inference efficiency on NVIDIA hardware.
Model overview
Context window
128K
tokens
Input price
—
quoted on request
Output price
—
quoted on request
Weekly volume
—
tokens / week
Open weights
Yes
self-hostable
Capabilities
4
of 11 tags
Description
Nemotron Super is a reasoning model from NVIDIA. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. NVIDIA’s stated focus is open reasoning models tuned for its stack. Its mean it can also be self-hosted under its licence.
Capabilities
- Reasoning
- Spends extra billed tokens thinking before it answers, trading latency and cost for accuracy.
- Tool calling
- Calls functions you define and returns their arguments as structured data, the basis of agents.
- Streaming
- Emits tokens as they are generated, so answers appear progressively rather than all at once.
- Open weights
- The parameters are published, so the model can be inspected, fine-tuned and self-hosted under its licence.
Strengths & weaknesses
Strengths
- Free at point of use
- Reference-grade efficiency
- Open weights
Weaknesses
- Rate limits on free tier
- Ceiling trails paid reasoning models
Pricing
| Rate | Price | Unit |
|---|---|---|
| Input | — quoted on request | — |
| Output | — quoted on request | — |
This model is not provisioned yet; the rate is quoted on request.
Context window
128Ktokens
covers prompt and response together, so a long input leaves less room for the answer.
Supported features
| Feature | Support |
|---|---|
| Tool calling | Supported |
| JSON mode | Not supported |
| Streaming | Supported |
| Vision input | Not supported |
| Audio input | Not supported |
| Long context | Not supported |
| Open weights | Supported |
| Reasoning | Supported |
| Fine-tunable | Not supported |
| Batch | Not supported |
| Caching | Not supported |
Example use cases
Prototyping reasoning flows
Self-hosted inference
Education
Comparison
Compare against anything →| Attribute | Nemotron Super | GLM-4.5 Air | DeepSeek R1 |
|---|---|---|---|
| Context window | 128K | 128K | 164K |
| Input price | R0.00 | R0.00 | R0.00 |
| Output price | — not charged | — not charged | — not charged |
| Tool calling | Supported | Supported | Supported |
| JSON mode | Not supported | Not supported | Not supported |
| Vision input | Not supported | Not supported | Not supported |
| Open weights | Supported | Supported | Supported |
| Prompt caching | Not supported | Not supported | Not supported |
Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.
Provider information
View NVIDIA →NVIDIA · Santa Clara, United States · est. 1993 (Nemotron open-model programme from 2024)
NVIDIA's Nemotron programme releases open reasoning models engineered to run superbly on its own hardware, free to use, meticulously optimised, and intended to grow the total market for accelerated inference. One model, deliberately: a reference implementation of efficient open reasoning.
Recent releases
Documentation
Frequently asked questions
Input is billed at R0.00 per 1M tokens, and there is no separate output charge. Every figure on this page is an illustrative placeholder.
Yes. Nemotron Super's parameters are published, so it can be downloaded, inspected, fine-tuned and self-hosted under its licence. Self-hosting trades per-token pricing for infrastructure you run.
Prompt and response share one window: Nemotron Super accepts up to 128K tokens in total, so a long input leaves less room for the answer. The median across reasoning models is 200K. Recall is strongest well inside the limit. Test at your real prompt depth before relying on the ceiling.
GLM-4.5 Air is the closest neighbour in the catalogue, with 128K of context at R0.00 per 1M tokens in. Put both in a comparison before wiring a fallback chain, so the trade-off is a decision rather than a default.