AI Model APIs
AI Model APIsProviders
AI Model APIs

The complete platform for comparing AI models. Find pricing, capabilities, and the perfect model for your use case.

contact@aimodelapis.com

Resources

  • AI Models APIs
  • Providers

About

  • About
  • Contact
  • Privacy Policy
  • Terms of Service

© 2026 AI Model APIs. All rights reserved.

Back to Models
Venice AI

NVIDIA Nemotron 3 Ultra API

Venice AI
About

Build advanced reasoning agents with NVIDIA Nemotron 3 Ultra, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.63/1M input and $3.13/1M output tokens, native tool calling support, open weights architecture. Access NVIDIA Nemotron 3 Ultra via the Venice AI API with up to 33K output tokens.

Capabilities

Input Modalities

text

Output Modalities

text
Reasoning
Yes
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
256K

Tokens

Input Limit
256K

Tokens

Max Output
33K

Tokens

Pricing

Standard (per 1M tokens)

Input
$0.63
Output
$3.13

Caching (per 1M tokens)

Read
$0.19
Frequently Asked Questions

NVIDIA Nemotron 3 Ultra by Venice AI costs $0.63 per 1M input tokens and $3.13 per 1M output tokens. Cached reads cost $0.19 per 1M tokens.

Model Details
ID
nvidia-nemotron-3-ultra-550b-a55b
Provider
Venice AI
Family
nemotron
Release Date
Jun 4, 2026
Knowledge Cutoff
N/A
API Integration
NPM Package
venice-ai-sdk-provider
Environment Variables
VENICE_API_KEY
Documentation