Nemotron 3 Super model profile
Evidence snapshot:
Nemotron 3 Super is a NVIDIA model profile with a 1,000,000-token context window. The dated catalog snapshot records text modalities and interfaces for reasoning controls, structured output, text generation, tool calling.
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
Nemotron 3 Super is a reference profile: NVIDIA publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
Nemotron 3 Super is an independent knowledge profile. It does not claim that Kendr hosts the model, quote a Kendr customer price, promise API availability, or advertise a Kendr routing receipt.
Nemotron 3 Super accepts text and returns text. The snapshot records reasoning controls, structured output, text generation, and tool calling as capabilities or interfaces.
The dated reference snapshot lists $0.085 input and $0.4 output per million tokens. Cached input is $0.06 per million tokens.
The 2026-09-06 snapshot includes 2 Artificial Analysis indexes. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
No comparable popularity rank or traffic share is present in the 2026-09-06 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated.
Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.
Profile facts
- Profile type
- Model research profile
- Provider or publisher
- NVIDIA
- Context window
- 1,000,000 tokens
- Snapshot date
- 2026-09-06
- Knowledge cutoff
- Not disclosed
- Reference catalog ID
- nvidia/nemotron-3-super-120b-a12b
When to pick Nemotron 3 Super
Nemotron 3 Super is a reference profile: NVIDIA publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.
- Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
- Reach for it when you want to trade depth against cost per call. Reasoning effort is selectable across medium, low, so one route can serve both cheap and deep work.
- Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
Context, modalities, and identity
Nemotron 3 Super accepts text and returns text. The snapshot records reasoning controls, structured output, text generation, and tool calling as capabilities or interfaces.
- Provider or publisher
- NVIDIA
- Context window
- 1,000,000 tokens
- Maximum output
- 16,384 tokens
- Input modalities
- text
- Output modalities
- text
- Knowledge cutoff
- Not disclosed
Model overview
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
- Reference model ID
- nvidia/nemotron-3-super-120b-a12b
- Canonical version
- nvidia/nemotron-3-super-120b-a12b-20230311
- Hugging Face ID
- nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
Capabilities and supported controls
Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- reasoning controls
- structured output
- text generation
- tool calling
Dated pricing snapshot
The dated reference snapshot lists $0.085 input and $0.4 output per million tokens. Cached input is $0.06 per million tokens.
These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price.
- Price date
- 2026-09-06
- Input
- $0.085 per 1M tokens
- Cached input
- $0.06 per 1M tokens
- Output
- $0.4 per 1M tokens
Provider routes, performance, and uptime
The snapshot retains 2 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.
- Active provider endpoints
- 2
- Best p50 latency
- No recent metric
- Best p50 throughput
- No recent metric
- Availability with routing
- No recent metric
- Availability without routing
- No recent metric
- Performance date
- 2026-09-06
| Provider | Quantization | Input / 1M | Output / 1M | Cache read / 1M | Context | p50 latency | p50 throughput | Uptime (1d) |
|---|---|---|---|---|---|---|---|---|
| DeepInfra | bf16 | $0.085 / 1M | $0.4 / 1M | No verified rate | 262,144 tokens | No recent p50 | No recent p50 | 99.99% |
| DigitalOcean | unknown | $0.3 / 1M | $0.65 / 1M | $0.06 / 1M | 1,000,000 tokens | No recent p50 | No recent p50 | 99.66% |
Benchmark evidence and limitations
The 2026-09-06 snapshot includes 2 Artificial Analysis indexes. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
- Coding Index
- 37.7
- Agentic Index
- 4.2
Popularity and market context
No comparable popularity rank or traffic share is present in the 2026-09-06 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated.
- Third-party catalog rank
- No verified rank
- Global market share
- Not inferred
- Observation date
- 2026-09-06
Frequently asked questions
When should I use Nemotron 3 Super?
Nemotron 3 Super is a reference profile: NVIDIA publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose. Reach for it when you want to trade depth against cost per call: Reasoning effort is selectable across medium, low, so one route can serve both cheap and deep work. Look elsewhere when you need to call it through Kendr today: This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
What is Nemotron 3 Super?
Nemotron 3 Super is a NVIDIA model profile with a 1,000,000-token context window. The dated catalog snapshot records text modalities and interfaces for reasoning controls, structured output, text generation, tool calling.
What context window does Nemotron 3 Super have?
The dated profile lists 1,000,000 tokens of context and up to 16,384 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.
What benchmark evidence is available for Nemotron 3 Super?
The 2026-09-06 snapshot includes 2 Artificial Analysis indexes. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
Is Nemotron 3 Super available through Kendr?
This is an independent knowledge profile, not a Kendr-hosted availability claim. Check Kendr's live public model API for currently enabled Kendr aliases.
Does the popularity rank represent Nemotron 3 Super's global market share?
No comparable popularity rank or traffic share is present in the 2026-09-06 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated. No global market-share percentage is inferred when the source does not publish one.
Sources and evidence dates
- Nemotron 3 Super third-party catalog record (catalog, checked 2026-09-06)
- Third-party model catalog methodology (methodology, checked 2026-09-06)
- NVIDIA official model documentation (primary, checked 2026-09-06)
- Artificial Analysis capability indices methodology (benchmark, checked 2026-09-06)