Overall score
LMSpeed rank: #93 / 96Updated: Jul 9, 2026Confidence: 1
8719.0
8719.0
8918.0
9014.0
9111.0
9111.0
93Nemotron 3 Super10.0
945.0
945.0
964.0
Nemotron 3 Super benchmark, API pricing, and provider data cover 18 API providers, with input prices starting at $0.010/M. Nemotron 3 Super free API options are available from 4 providers.
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 Mam...
Scores across benchmark categories on a 0-100 scale.
No benchmark category data yet.
Input and output token limits for this model, plus how it ranks on long-context understanding.
1 metric
Compare Nemotron 3 Super API pricing across 14 providers. Input prices range from $0.010 to $499.50 per million input. 素墨API offers the lowest rate at $0.010/M. 4 providers offer free API credits or a free tier.
| Provider | Model Variant | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit | |
|---|---|---|---|---|---|---|---|
CM-API 公益站 Free | nvidia/nemotron-3-super-120b-a12b:free | $0.0000/M | $0.0000/M | 92.8% | — | — | — |
梦德 API Free | nemotron-3-super-120b-a12b | $0.0000/M | $0.0000/M | 100% | — | — | — |
| nvidia/nemotron-3-super-120b-a12b | $0.0000/M | $0.0000/M | 100% | — | — | — | |
霸气公益平台 Free | nemotron-3-super-120b-a12b | $0.0000/M | $0.0000/M | 99.4% | — | — | — |
| nemotron-3-super-120b-a12b | $0.010/M | $0.010/M | 100% | — | — | — | |
| nvidia/nemotron-3-super-120b-a12b:free | $0.010/M | $0.010/M | 99.9% | — | — | — | |
| nvidia/nemotron-3-super-120b-a12b | $0.050/M | $0.250/M | 99.7% | — | — | — | |
| nvidia/nemotron-3-super-120b-a12b | $0.090/M | $0.450/M | 99.8% | — | — | — | |
| nvidia/nemotron-3-super-120b-a12b | $0.090/M | $0.450/M | 99.5% | — | — | — | |
| nvidia/nemotron-3-super-120b-a12b | $0.200/M | $1.00/M | 99.6% | — | — | — | |
| nvidia/nemotron-3-super-120b-a12b | $1.00/M | $1.00/M | 90.9% | — | — | — | |
| nvidia/nemotron-3-super-120b-a12b | $30.00/M | $30.00/M | 99.9% | — | — | — | |
| nvidia/nemotron-3-super-120b-a12b:free | $75.00/M | $75.00/M | 99.5% | — | — | — | |
| nvidia/nemotron-3-super-120b-a12b | $75.00/M | $75.00/M | 100% | — | — | — | |
| kai/nvidia/nemotron-3-super-120b-a12b:free | $75.00/M | $75.00/M | — | — | — | — | |
| or/nvidia/nemotron-3-super-120b-a12b:free | $75.00/M | $75.00/M | — | — | — | — | |
| nvidia/nemotron-3-super-120b-a12b:free | $75.00/M | $75.00/M | 0% | — | — | — | |
| nvidia/nemotron-3-super-120b-a12b | $499.50/M | $2497.50/M | 99.5% | — | — | — |
gpt-oss
GPT-OSS is an open-weight language model family designed for self-hosted inference, research, and cost-efficient alternatives to proprietary GPT-class models.
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
qwen3-5
Alibaba Qwen3.5 is a Qwen3 generation model with improved reasoning, multilingual support, and efficient inference for chat, coding, and agent applications.
minimax-m2-5
MiniMax M2.5 is MiniMax's flagship text model for coding and agents, with SOTA-level programming and agentic performance, improved token efficiency, and fast high-TPS API deployment.
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
deepseek-v4-pro
DeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.
