Using Nemotron 3 Ultra on Venice AI

Implementation guide · Nemotron 3 · NVIDIA AI

ServerlessOpen Weights

Venice AI exposes Nemotron 3 Ultra through model ID nvidia-nemotron-3-ultra-550b-a55b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-17. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Venice AI and generate an API key.
  2. 2
    Use the Venice AI SDK or REST API to call nvidia-nemotron-3-ultra-550b-a55b — see the documentation for request format.
  3. 3
    You'll be billed $0.63/1M input, $3.13/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See Venice AI documentation for integration details.

Pricing on Venice AI

TypePrice (per 1M)
Input tokens$0.63
Output tokens$3.13

Capabilities

ReasoningJSON / Tool use

About Nemotron 3 Ultra

NVIDIA's open frontier-reasoning model (550B total / 55B active MoE, hybrid Transformer-Mamba). Highest Artificial Analysis Intelligence Index for any US open model (score: 48). 300+ tokens/second. 1M-token context. Announced at Computex 2026. Pricing: ~$0.60/$2.60 per 1M tokens (provider median); free tier on some providers.

Full model details →

Model Specs

Released2026-06-04
Parameters550B
Context1M
ArchitectureMixture of Experts

Also available on(7)

DeepInfra$0.50/1MWeights & Biases$0.50/1MBaseten API$0.60/1M
Compare all providers →

Provider

Venice AI