ModelBench
NVIDIA logo
Models/NVIDIA

NVIDIA: NVIDIA: Nemotron 3 Super (free)

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...

Source-linked Weight access not listed
API record Report
InputT
OutputT
Input priceFree
Output priceFree
Context262.144K
Max output235.929K
Providers0
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
No inference providers are listed

The model record exists, but no source-linked provider offer is available yet.

Submit a source
Specification

Capabilities

Recorded from the source catalog and provider listings.

? Reasoning Unknown
? Tool calling Unknown
? Structured output Unknown
? Attachments Unknown
× Vision input No
? Open weights Unknown
Creator
NVIDIA
Model family
Not documented
Knowledge cutoff
Not documented
License
Not documented
Release date
Not documented
Model ID
nvidia/nemotron-3-super-120b-a12b:free
Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
Benchmark profile
Coding IndexCoding Index Agentic IndexAgentic Index IntelligenceIntelligence Index This model — Coding Index: 37.7 index (36.6th percentile) This model — Agentic Index: 4.1 index (26.9th percentile) This model — Intelligence Index: 13.6 index (19.8th percentile)

Each axis is this model's percentile among the 3 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

Coding Index index Source ↗
Coding Index #130 of 205
Agentic Index index Source ↗
Agentic Index #141 of 193
Intelligence Index index Source ↗
Intelligence Index #153 of 192

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against Coding Index, the benchmark with the widest published coverage that this model appears in.

0 43 86 $0.01 $0.1 $1 $10 Claude Opus 5 (batch) — $2.5/M, score 78.0 OpenAI: GPT-5.6 Sol (batch) — $1/M, score 77.4 Nemotron 3.5 Lightning 30B A3B — $0.05/M, score 26.8 Google: Gemini 3.6 Flash (batch) — $0.375/M, score 69.2 MiniMax: MiniMax M2.7 — $0.3/M, score 52.6 GPT-4.1 nano — $0.1/M, score 11.1 OpenAI: GPT-4o-mini (batch) — $0.075/M, score 11.4 DeepSeek V3.2 — $0.18/M, score 44.2 Nemotron 3 Ultra 550B A55B — $0.5/M, score 49.3 Nemotron 3 Nano 30B A3B — $0.05/M, score 14.4 Gemini 3.1 Flash Lite Preview — $0.25/M, score 34.7 Gemini 2.5 Pro — $1.25/M, score 33.3 OpenAI: o3 Mini High (batch) — $0.55/M, score 16.3 Qwen: Qwen3.8 Max (0902) — $2/M, score 71.8 Nemotron 3 Super 120B A12B — $0.2/M, score 37.7 DeepSeek V4 Pro — $0.435/M, score 59.4 GPT-4o (2024-05-13) — $5/M, score 24.2 GPT-5.4 — $2.5/M, score 71.1 GPT-4 Turbo — $10/M, score 21.5 SpaceXAI: Grok 4.5 — $2/M, score 72.4 Anthropic: Claude Sonnet 5 (batch) — $1/M, score 71.5 OpenAI: o1 (batch) — $7.5/M, score 39.7 GPT-4o mini — $0.15/M, score 11.4 MiniMax: MiniMax M3 (batch) — $0.3/M, score 58.6 GPT-5.4 nano — $0.2/M, score 56.1 Anthropic: Claude Opus 4.8 — $5/M, score 74.3 OpenAI: GPT-5.5 (batch) — $2.5/M, score 74.9 GPT-5 — $1.25/M, score 37.8 DeepSeek V4 Flash — $0.15/M, score 52.0 Gemini 3.8 Flash — $0.75/M, score 76.3 LongCat-2.0 — $0.3/M, score 45.3 Kimi K3 — $3/M, score 76.2 Z.ai: GLM 5.3 Flash — $0.15/M, score 71.5 Claude Sonnet 5 — $2/M, score 71.5 Gemini 3.7 Flash — $0.75/M, score 76.1 OpenAI: GPT-5.4 Nano (batch) — $0.1/M, score 56.1 Inkling — $1.87/M, score 52.1 Mistral: Ministral 3 8B 2512 — $0.15/M, score 9.7 Gemma 3 12B IT — $0.05/M, score 5.8 Qwen: Qwen3.5-9B (batch) — $0.17/M, score 28.7 OpenAI: GPT-4 Turbo (batch) — $5/M, score 21.5 OpenAI: GPT-3.5 Turbo (batch) — $0.25/M, score 10.7 Anthropic: Claude Fable 5.1 (batch) — $5/M, score 81.6 Gemma 3 4B IT — $0.04/M, score 2.7 Anthropic: Claude Opus 4.7 — $5/M, score 73.6 MiniMax: MiniMax M3 — $0.3/M, score 58.6 DeepSeek: DeepSeek V4 Pro 0813 (batch) — $0.66/M, score 68.8 Anthropic: Claude Opus 4.8 (batch) — $2.5/M, score 74.3 Gemma 4 31B IT — $0.09/M, score 43.4 Anthropic: Claude Fable 5.1 — $10/M, score 81.6 Google: Gemma 4 31B (batch) — $0.39/M, score 43.4 Qwen: Qwen3.8 2.4T A95B (batch) — $2/M, score 71.9 Mistral: Devstral 2 2512 — $0.4/M, score 31.3 MoonshotAI: Kimi K2.7 Code (batch) — $0.95/M, score 60.8 MiMo-V2.5 — $0.14/M, score 56.8 GPT-3.5-turbo — $0.5/M, score 10.7 Google: Gemini 3.5 Flash Lite (batch) — $0.15/M, score 49.3 Kimi K2 Thinking — $0.4/M, score 21.0 Mistral: Mistral Medium 3.5 (batch) — $0.75/M, score 46.9 Qwen: Qwen3.8 Max (0803) — $2/M, score 68.9 Mistral: Mistral Medium 3.1 (batch) — $0.2/M, score 20.5 OpenAI: GPT-5.6 Terra (batch) — $1/M, score 76.7 Kimi K2.7 Code — $0.95/M, score 60.8 Google: Gemini 3.8 Flash (batch) — $0.375/M, score 76.3 Google: Gemini 3.1 Pro Preview (batch) — $1/M, score 68.8 Gemma 4 26B A4B IT — $0.042/M, score 39.3 GPT OSS 20B — $0.02/M, score 20.7 Z.ai: GLM 5.3 Flash (batch) — $0.075/M, score 71.5 inclusionAI: Ling 3.0 Flash VL — $0.06/M, score 57.0 SpaceXAI: Grok 4.6 — $2/M, score 76.8 Gemini 3.5 Flash Lite — $0.3/M, score 49.3 Inkling Small — $0.45/M, score 52.9 MoonshotAI: Kimi K3 (batch) — $3/M, score 76.2 Qwen: Qwen3.7 Plus — $0.32/M, score 55.9 Gemini 3.5 Flash — $1.5/M, score 70.1 Qwen: Qwen3.6 Plus — $0.325/M, score 54.5 Qwen: Qwen3.8 27B — $0.42/M, score 68.1 Anthropic: Claude Opus 4.7 (batch) — $2.5/M, score 73.6 GPT-5.6 Sol — $4/M, score 77.4 Anthropic: Claude Fable 5 (batch) — $5/M, score 76.5 IBM: Granite 4.2 8B — $0.06/M, score 22.4 Mistral: Mistral Large 3 2512 (batch) — $0.25/M, score 20.1 OpenAI: GPT-5.1 (batch) — $0.625/M, score 49.4 Anthropic: Claude Sonnet 4.5 — $3/M, score 52.1 Qwen: Qwen3 14B — $0.227/M, score 13.8 Mistral: Mistral Medium 3.1 — $0.4/M, score 20.5 Google: Gemini 3.7 Flash (batch) — $0.375/M, score 76.1 GPT-5 Mini — $0.25/M, score 15.6 OpenAI: GPT-4.1 Nano (batch) — $0.05/M, score 11.1 OpenAI: GPT-6 Astra (batch) — $5/M, score 76.9 Claude Fable 5 — $10/M, score 76.5 Gemma 3 27B IT — $0.08/M, score 10.1 Anthropic: Claude Sonnet 4.6 — $3/M, score 63.0 Muse Spark 1.1 — $1.25/M, score 71.3 DeepSeek V4 Pro 0813 — $0.442/M, score 68.8 DeepSeek-R1 — $0.7/M, score 24.6 GPT-4.1 mini — $0.4/M, score 20.2 Google: Gemini 3.5 Flash (batch) — $0.75/M, score 70.1 Z.ai: GLM 5.3 (batch) — $0.7/M, score 74.8 Z.ai: GLM 5.3 — $1.4/M, score 74.8 Z.ai: GLM 5.2 (batch) — $0.7/M, score 68.8 SpaceXAI: Grok 4.3 — $1.25/M, score 42.2 Z.ai: GLM 5.1 — $0.966/M, score 55.8 GPT-5.6 Terra — $2/M, score 76.7 OpenAI: GPT-5.4 (batch) — $1.25/M, score 71.1 OpenAI: GPT-5 Mini (batch) — $0.125/M, score 15.6 NVIDIA: Nemotron 3 Ultra (batch) — $0.6/M, score 49.3 OpenAI: gpt-oss-120b (batch) — $0.15/M, score 30.4 GPT-4 — $30/M, score 13.1 Thinking Machines: Inkling Small (batch) — $0.5/M, score 52.9 Mistral: Mistral Small 4 (batch) — $0.075/M, score 26.6 DeepSeek: DeepSeek V4 Flash 0731 (batch) — $0.11/M, score 69.1 Thinking Machines: Inkling (batch) — $1/M, score 52.1 Anthropic: Claude Sonnet 4.6 (batch) — $1.5/M, score 63.0 Google: Gemini 2.5 Pro (batch) — $0.625/M, score 33.3 Gemini 3.1 Pro Preview — $2/M, score 68.8 Kimi K2.5 — $0.3/M, score 46.8 Mistral: Mistral Large 3 2512 — $0.5/M, score 20.1 DeepSeek: DeepSeek V3.1 Terminus — $0.27/M, score 43.5 OpenAI: gpt-oss-20b (batch) — $0.05/M, score 20.7 SpaceXAI: Grok 4.3 (batch) — $1/M, score 42.2 Anthropic: Claude Haiku 4.5 (batch) — $0.5/M, score 43.9 Anthropic: Claude Sonnet 4.5 (batch) — $1.5/M, score 52.1 Claude Opus 5 — $5/M, score 78.0 Gemini 3.6 Flash — $0.75/M, score 69.2 inclusionAI: Ling 3.0 Flash — $0.021/M, score 50.6 Muse Spark 1.2 — $1.25/M, score 72.2 OpenAI: GPT-5.6 Luna (batch) — $0.1/M, score 71.4 OpenAI: GPT-5.4 Mini (batch) — $0.375/M, score 56.1 DeepSeek V4 Flash 0731 — $0.035/M, score 69.1 GPT-6 Astra — $10/M, score 76.9 GPT-5.1 — $1.25/M, score 49.4 Qwen: Qwen3 Next 80B A3B Thinking — $0.15/M, score 17.4 Qwen: Qwen3.8 2.4T A95B — $2/M, score 71.9 GPT-5.5 — $5/M, score 74.9 Kimi K2.6 — $0.95/M, score 61.8 Mistral: Ministral 3 8B 2512 (batch) — $0.075/M, score 9.7 Solar Pro 4 — $0.3/M, score 52.7 Hy3 preview — $0.066/M, score 58.8 OpenAI: GPT-4.1 Mini (batch) — $0.2/M, score 20.2 GPT OSS 120B — $0.03/M, score 30.4 Inception: Mercury 2 — $0.25/M, score 31.1 o1 — $15/M, score 39.7 MiMo-V2.5-Pro — $0.435/M, score 60.2 GPT-5.6 Luna — $0.2/M, score 71.4 Z.ai: GLM 4.6 — $0.43/M, score 45.8 OpenAI: GPT-5 (batch) — $0.625/M, score 37.8 Anthropic: Claude Sonnet 4 — $3/M, score 37.6 GPT-5.4 mini — $0.75/M, score 56.1 Trinity Large Thinking — $0.25/M, score 25.8 Qwen: Qwen3 30B A3B Thinking 2507 — $0.2/M, score 12.1 Z.ai: GLM 5.2 — $0.6/M, score 68.8 Qwen: Qwen3.7 Max — $1.475/M, score 66.0 SpaceXAI: Grok Build 0.1 — $1/M, score 51.5 Qwen: Qwen3.6 35B A3B — $0.1/M, score 41.9 Qwen: Qwen3.6 27B — $0.3/M, score 53.7 inclusionAI: Ling-2.6-flash — $0.01/M, score 25.3 Mistral: Mistral Small 4 — $0.15/M, score 26.6 Kwaipilot: KAT-Coder-Pro V2 — $0.3/M, score 59.5 Qwen: Qwen3.5-9B — $0.1/M, score 28.7 Qwen: Qwen3.5-35B-A3B — $0.312/M, score 37.0 Qwen: Qwen3.5-122B-A10B — $0.26/M, score 45.7 Upstage: Solar Pro 3 — $0.15/M, score 16.2 Z.ai: GLM 4.7 — $0.4/M, score 45.3 Amazon: Nova 2 Lite — $0.3/M, score 23.0 Mistral: Ministral 3 3B 2512 — $0.1/M, score 4.8 Google: Gemma 3n 4B — $0.06/M, score 3.2 Meta: Llama 4 Maverick — $0.2/M, score 16.3 OpenAI: o3 Mini High — $1.1/M, score 16.3 Meta: Llama 3.3 70B Instruct — $0.1/M, score 11.9 Meta: Llama 3.1 8B Instruct — $0.05/M, score 5.4 Nex AGI: Nex-N2-Pro — $0.25/M, score 59.1 Mistral: Mistral Medium 3.5 — $1.5/M, score 46.9 inclusionAI: Ring-2.6-1T — $0.075/M, score 42.8 IBM: Granite 4.1 8B — $0.05/M, score 9.5 Qwen: Qwen3.5 397B A17B — $0.55/M, score 48.2 Qwen: Qwen3 Coder Next — $0.12/M, score 36.2 Mistral: Ministral 3 14B 2512 — $0.2/M, score 14.4 Anthropic: Claude Haiku 4.5 — $1/M, score 43.9 Qwen: Qwen3 235B A22B Thinking 2507 — $0.23/M, score 22.1 Qwen: Qwen3 8B — $0.117/M, score 9.0 Qwen: Qwen3 32B — $0.08/M, score 15.3 Meta: Llama 4 Scout — $0.1/M, score 8.2 DeepSeek: DeepSeek V3 0324 — $0.25/M, score 21.2 Cohere: Command A — $2.5/M, score 27.8 Step 3.7 Flash — $0.185/M, score 39.6 Input price per million tokens (log scale) Index

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
Max Output Tokens262144 → 235929
Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/nvidia/nemotron-3-super-120b-a12b:free
curl
curl "https://model.kyssta.lol/api/v1/models/nvidia/nemotron-3-super-120b-a12b:free"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is NVIDIA: Nemotron 3 Super (free)?

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. It is published by NVIDIA and catalogued here from OpenRouter.

How much does NVIDIA: Nemotron 3 Super (free) cost?

This model is documented as free to use at the listed providers.

What is the context length of NVIDIA: Nemotron 3 Super (free)?

NVIDIA: Nemotron 3 Super (free) accepts up to 262.144K tokens of context and returns up to 235.929K output tokens.

More models from NVIDIA

View all →
NVIDIA: Nemotron Nano 9B V2 (free)

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...

128K ctx Mistral Nemotron

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

128K ctx Llama 3.3 Nemotron Super 49B v1.5

Nemotron model for efficient reasoning, coding, and specialized AI agents

131.072K ctx $0.4/M in NVIDIA: Nemotron 3 Nano Omni (free)

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...

256K ctx