NVIDIA logo

NVIDIA AI models

7 NVIDIA models on FastRouter, all behind one OpenAI-compatible API. Compare pricing, context windows and benchmarks, then open any model for its providers and code samples.

Filter in catalog
Models
7
Largest context
1.05M
Nemotron 3 Nano 30B (Free)
Lowest input /1M
$0.06
Nemotron 3.5 Lightning
Top intelligence
13.6
Nemotron 3.5 Super VL

All NVIDIA models

NVIDIA logo

NVIDIA Nemotron 3.5 Super VL is an open multimodal 120B-parameter Mixture-of-Experts model (12B active) for agents that see, reason, and act. It understands text, images, documents, GUIs, and video, and adds reasoning and tool use.

nvidia/nemotron-3.5-super-vlSep 16, 2026
Context
262K
Price /1M
$0.15 in$0.50 out
Intel
13.6
NVIDIA logo

NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks, with up to 4x higher throughput on a 1M-token context.

nvidia/nemotron-3.5-lightningAug 3, 2026
Context
262K
Price /1M
$0.06 in$0.16 out
Intel
5.5
NVIDIA logo

NVIDIA Nemotron 3 Nano 30B is a hybrid Mamba-2/MoE/Attention model with 3.5B active parameters, trained from scratch as a unified model for both reasoning and non-reasoning tasks. Reasoning traces can be toggled via a chat template flag, and the model supports tool use within a 1M-token context window, making it well suited for specialized agentic applications.

nvidia/nemotron-3-nano-30b:freeJul 9, 2026
Context
1.05M
Price /1M
Free
Intel
—
NVIDIA logo

NVIDIA Nemotron 3 Super is a 120B-parameter open mixture-of-experts model that activates just 12B parameters per token, delivering high compute efficiency and strong reasoning, agentic, and conversational capabilities for complex multi-agent applications. It supports tool use, thinking/reasoning traces, and a large 262K-token context window, and is optimized for collaborative agents and high-volume workloads such as IT ticket automation.

nvidia/nemotron-3-super:freeJul 9, 20263.1s latency
Context
262K
Price /1M
Free
Intel
—
NVIDIA logo

Nemotron Content Safety 3.5 is a compact multimodal safety classifier handling text, images and custom policies, with a safe/unsafe verdict plus reasoning trace.

nvidia/nemotron-content-safety-3.5Jun 1, 2026
Context
131K
Price /1M
$0.20 in$0.20 out
Intel
—
NVIDIA logo

Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows, with up to 5x faster inference and up to 30% lower cost for agentic workloads.

nvidia/nemotron-3-ultra-550b-a55bMay 16, 2026
Context
262K
Price /1M
$0.50 in$2.20 out
Intel
11.8
NVIDIA logo

NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts model engineered for compute efficiency and accuracy in multi-agent and specialized agentic systems, with strong reasoning, tool use and instruction following.

nvidia/nemotron-3-superMar 10, 2026
Context
262K
Price /1M
$0.07 in$0.40 out
Intel
—

Frequently asked questions

Model scores sourced from ArtificialAnalysis

NVIDIA AI Models: API Pricing & Benchmarks | FastRouter.ai