TokenRate

NVIDIA API Pricing

NVIDIA publishes the open Nemotron family — models post-trained for reasoning, agentic workflows, and tool use, including Llama-Nemotron variants. They're designed to run efficiently on NVIDIA hardware and are freely available for self-hosting.

Official site: build.nvidia.com →

Cheapest

Nemotron 3 Nano 30B A3B

$0.050/1M in

Flagship

Nemotron 3 Ultra

$0.500/1M in

Models

4 tracked

All tiers, latest pricing.

All NVIDIA Models

ModelTierInput / 1MOutput / 1MContext
Nemotron 3 Nano 30B A3Bfast$0.050$0.200262K
Nemotron 3 Superfast$0.085$0.4001M
Llama 3.3 Nemotron Super 49B V1.5balanced$0.400$0.400131K
Nemotron 3 Ultraflagship$0.500$2.201M

Model Details

Nemotron 3 Nano 30B A3B

$0.050 in

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.

Nemotron 3 Super

$0.085 in

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.

Llama 3.3 Nemotron Super 49B V1.5

$0.400 in

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context.

Nemotron 3 Ultra

$0.500 in

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

Calculate NVIDIA API Costs

Use the TokenRate calculator to estimate exactly what NVIDIA models will cost for your workload.

Open Calculator →

Other Providers

Anthropic pricing19 Anthropic models with full pricing.OpenAI pricing61 OpenAI models with full pricing.Google pricing29 Google models with full pricing.Meta pricing12 Meta models with full pricing.DeepSeek pricing11 DeepSeek models with full pricing.xAI pricing7 xAI models with full pricing.Mistral pricing22 Mistral models with full pricing.Qwen pricing47 Qwen models with full pricing.Cohere pricing6 Cohere models with full pricing.Amazon pricing5 Amazon models with full pricing.Microsoft pricing2 Microsoft models with full pricing.Zhipu AI pricing12 Zhipu AI models with full pricing.Moonshot AI pricing6 Moonshot AI models with full pricing.MiniMax pricing8 MiniMax models with full pricing.Perplexity pricing5 Perplexity models with full pricing.Nous Research pricing4 Nous Research models with full pricing.ByteDance pricing5 ByteDance models with full pricing.Arcee AI pricing4 Arcee AI models with full pricing.AI21 Labs pricing1 AI21 Labs models with full pricing.Reka AI pricing2 Reka AI models with full pricing.IBM pricing2 IBM models with full pricing.Tencent pricing2 Tencent models with full pricing.Inflection AI pricing2 Inflection AI models with full pricing.Liquid AI pricing1 Liquid AI models with full pricing.Allen Institute for AI pricing1 Allen Institute for AI models with full pricing.Baidu pricing1 Baidu models with full pricing.Writer pricing1 Writer models with full pricing.Upstage pricing1 Upstage models with full pricing.