NVIDIA Reasoning Model text vision

Nemotron 3.5 Super VL Pricing & Token Costs

Official API rate card for Nemotron 3.5 Super VL provided by NVIDIA. All token pricing is normalized per 1 Million tokens ($/1M).

Token Pricing Rates ($/1M Tokens)

Input Tokens 0.1000 per 1M tokens
Output Tokens 0.4000 per 1M tokens
Prompt Cache Read $0.0800 per 1M tokens
Prompt Cache Write Not Supported per 1M tokens

Technical Specifications

Provider
NVIDIA
Context Window
1,049k tokens (1,048,576)
Max Output Tokens
33k tokens (32,768)
Reasoning Architecture
Yes
Supported Modalities
text, vision

Estimated Inference Costs

Example cost calculation for standard application workloads assuming a 3:1 input-to-output token ratio.

100,000 requests (500 in / 150 out) 0.01
1,000,000 requests (1,000 in / 300 out) 0.22
← Compare Nemotron 3.5 Super VL on Master Pricing Table