Skip to main content

Nemotron 3 Super

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model that activates 12B parameters per token, built for complex multi-agent applications.

Input / output price
$0.102 / $0.48 per 1M
Context
262K tokens
Released
Mar 11, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "nemotron-3-super".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Inference.netinference_net/nemotron-3-super
$0.102/M$0.48/M

Pricing

USD per 1M tokens on Inference.net, after gateway discounts.

Input
$0.102 per 1M
Output
$0.48 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.102/MInference.net

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

10tokens/sacross providers

Faster than 33% of the other 596 models on the gateway

Response latency

Lower is better

1.3sacross providers

Faster than 57% of the other 758 models on the gateway

Benchmarks

The Respan Index plus 11 published scores from 3 sources, each linked to where it was published.

19.1/ 100

Respan Index#135 of 176

176 ranked models. The shaded band is this model's 95% interval, 12.6 to 34.2. GPT-4.1 and Qwen3.5-Plus fall inside it, so the gap is within the margin of error.
Nemotron 3 Super by category: Coding 4.4, Agents 17.1 (estimated), Reasoning 23.7, Knowledge & language 17.4, Human preference 40.3
  1. 135NVIDIA Nemotron 3 Super 120B-A12B19.1
  2. 134GPT-4.119.2
  3. 136Qwen3.5-Plus19.0

Published scores

BenchmarkScore
LiveCodeBenchbuild.nvidia.com81.2%
SWE-bench Verifiedbuild.nvidia.com60.5%
WeirdMLHåvard Tveit Ihle38%
Terminal-Bench Core 2.0build.nvidia.com31%

Compare Nemotron 3 Super: NVIDIA Nemotron 3 Super 120B-A12B vs NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4, NVIDIA Nemotron 3 Super 120B-A12B vs NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4, NVIDIA Nemotron 3 Super 120B-A12B vs NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4, NVIDIA Nemotron 3 Super 120B-A12B vs NVIDIA Nemotron 3 Nano 30B-A3B BF16

Apps

Use Nemotron 3 Super in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Nemotron 3 Super FAQ

Short answers, built from the data on this page.

Nemotron 3 Super is a model from NVIDIA, released on Mar 11, 2026. NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model that activates 12B parameters per token, built for complex multi-agent applications.

On the Respan gateway, Nemotron 3 Super costs $0.102 per 1M input tokens and $0.48 per 1M output tokens on Inference.net, after gateway discounts.

Nemotron 3 Super is served by Inference.net.

Nemotron 3 Super accepts up to 262K tokens of context.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "nemotron-3-super". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Nemotron 3 Super scores 19.1 out of 100 on the Respan Index v1.1, ranking #135 of 176 models. By category: Coding 4.4, Agents 17.1 (estimated), Reasoning 23.7, Knowledge & language 17.4, and Human preference 40.3. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Nemotron 3 Super has 11 published benchmark scores, including LiveCodeBench 81.2%, GPQA (with tools) 82.7%, and AIME 2025 (no tools) 90.2%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.