ModelBench
NVIDIA logo
Models/NVIDIA

Nemotron 3 Super 120B A12B

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

Source-linked nemotron Open weights Released 2026-03-11
API data Report
Input modalitiesT
Output modalitiesT
Input price$0.2/1M tokens
Output price$0.8/1M tokens
Context window262.144K
Max output262.144K
Overview

Capabilities and specifications

✓ Reasoning Yes
✓ Tool calling Yes
? Structured output Unknown
× Attachments No
× Vision input No
✓ Open weights Yes
Creator
NVIDIA
Model family
nemotron
Knowledge cutoff
Not documented
License
Not documented
Release date
2026-03-11
Model ID
nvidia/nemotron-3-super-120b-a12b
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering Nemotron 3 Super 120B A12B
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
Kenari nemotron-3-super-120b-a12b 262.144K Not listed Not listed - ReasoningTools Docs
NanoGPT nvidia/nemotron-3-super-120b-a12b 262.144K $0.05 $0.25 - ReasoningTools Docs
OpenRouter nvidia/nemotron-3-super-120b-a12b 1M $0.085 $0.4 - ReasoningToolsJSON Docs
Pioneer nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 1M $0.09 $0.45 $0.09 ReasoningTools Docs
Kilo Gateway nvidia/nemotron-3-super-120b-a12b 262.144K $0.1 $0.5 $0.1 ReasoningTools Docs
Vercel AI Gateway nvidia/nemotron-3-super-120b-a12b 256K $0.15 $0.65 - Reasoning Docs
Nvidia nvidia/nemotron-3-super-120b-a12b 262.144K $0.2 $0.8 - ReasoningTools Docs
Perplexity Agent nvidia/nemotron-3-super-120b-a12b 1M $0.25 $2.5 - ReasoningTools Docs
Cortecs nemotron-3-super-120b-a12b 262.144K $0.266 $0.799 - ReasoningTools Docs
Nebius Token Factory nvidia/nemotron-3-super-120b-a12b 256K $0.3 $0.9 - ReasoningToolsJSON Docs
Synthetic hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 262.144K $0.3 $1 $0.3 ReasoningTools Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
Agentic Index - Unversioned - indexTop 8 reported models
Claude Opus 5
55.3
GPT-5.6 Sol
54.0
Anthropic: Claude Fable 5 (batch)
52.8
Claude Fable 5
52.8
Kimi K3
50.1
GPT-5.6 Terra
47.4
Anthropic: Claude Opus 4.8 (batch)
47.2
Nemotron 3 Super 120B A12B
8.7
Coding Index - Unversioned - indexTop 8 reported models
Claude Opus 5
78.0
GPT-5.6 Sol
77.4
GPT-5.6 Terra
76.7
Anthropic: Claude Fable 5 (batch)
76.5
Claude Fable 5
76.5
Kimi K3
76.2
OpenAI: GPT-5.5 (batch)
74.9
Nemotron 3 Super 120B A12B
37.7
Intelligence Index - Unversioned - indexTop 8 reported models
Claude Opus 5
60.7
Anthropic: Claude Fable 5 (batch)
59.9
Claude Fable 5
59.9
GPT-5.6 Sol
58.9
Kimi K3
57.1
Anthropic: Claude Opus 4.8 (batch)
55.7
Anthropic: Claude Opus 4.8
55.7
Nemotron 3 Super 120B A12B
25.4
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
Max Output Tokens16384 → 262144
Price Completion0.39999999999999997 → 0.8
Price Prompt0.08499999999999999 → 0.2
Max Output Tokens262144 → 16384
Price Completion0.8 → 0.39999999999999997
Price Prompt0.2 → 0.08499999999999999
Max Output Tokens16384 → 262144
Price Completion0.39999999999999997 → 0.8
Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/nvidia/nemotron-3-super-120b-a12b
curl
curl "https://www.modelbench.lol/api/v1/models/nvidia/nemotron-3-super-120b-a12b"