Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b- NVIDIA
- Family · Nemotron 3 Super
- Open weights
- Text → Text
- Reasoning · adjustable
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context1M
Max output256K
Input / 1M$0.30
Output / 1M$2.408× input
Usage
Tokens / day1.3B▼ 22% 7d
Usage rank#185
Requests / day313.2K
Tool calls / req0.13
Per request · 30 days
Avg input6.0K0.4× median
Avg output729about median
Cache hit23%0.3× median
Reasoning share61%about median
Tool-call failures2.7%1.5× median
Consumption
Peak 2.6B 20 OctLow 931.9M 15 OctRank today #185
News & trends
Trending · 14 days
- Open vs closed AI: Nemotron 3 Super vs Mercury 2.5 code Star Fox13 views
- MiMo V2.6 vs Nemotron 3 Super coding test: The Legend of Zelda: A Link to the Past from one prompt75 views
News · latest from NVIDIA
- Accelerate agentic AI with NVIDIA Nemotron models on Amazon EKS and SageMaker HyperPod EKSAWS · 29 Oct
- NVIDIA Open Models Advance Europe’s Sovereign Intelligence Across IndustriesNVIDIA · 21 Oct
- NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal ReasoningNVIDIA · 15 Oct
- Open From Data Center to Desktop: NVIDIA Expands Nemotron Family With Highest Efficiency Super VL and Bolt ModelsNVIDIA · 15 Oct
Speed
Output speed#321/33418 tok/s3.5× slower than median
Fastest provider63 tok/sbest of 3 providers
First token#1030.69 s1.6× quicker than median
Technical details
- Reasoning
- on · medium
- Tokenizer
- Other
- License
- other
- Parameters
- 124B
- Moderation
- none
- Downloads · likes
- 51.9K · 293
Reasoning effort
- medium · default
- low
- none
Request parameters 20
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- reasoning_effort
- include_reasoning
- temperature
- top_p
- top_k
+10 more
- min_p
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Reasoning agents with toggled thinking
- Cost-aware tool-calling workflows
- Long document question answering
- Self-hosted text pipelines on open weights
Think twice for
- Image understanding
- Hardest frontier coding tasks
- Ultra-low-latency simple chat
Research papers
Social
Most watched and discussed · 90 days
- MiMo V2.6 vs Nemotron 3 Super coding test: The Legend of Zelda: A Link to the Past from one promptOpenLLMVS · 75 views · 20 Oct
- Open vs closed AI: Nemotron 3 Super vs Mercury 2.5 code Star FoxOpenLLMVS · 13 views · 21 Oct
Same family
Nemotron 3 Super- 12.8
Want Nemotron 3 Super on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.