Nemotron 3 Nano Omni 30B A3B Reasoning API
About
Build advanced reasoning agents with Nemotron 3 Nano Omni 30B A3B Reasoning, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.30/1M input and $1.83/1M output tokens, native tool calling support, open weights architecture. Access Nemotron 3 Nano Omni 30B A3B Reasoning via the Crusoe API with up to 66K output tokens.
Capabilities
Input Modalities
textimagevideoaudio
Limits
Context Window
256K
Tokens
Input Limit
256K
Tokens
Max Output
66K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.30
Output
$1.83
Caching (per 1M tokens)
Read
$0.30
Audio (per 1M tokens)
Input
$0.50
Frequently Asked Questions
Nemotron 3 Nano Omni 30B A3B Reasoning by Crusoe costs $0.30 per 1M input tokens and $1.83 per 1M output tokens. Cached reads cost $0.30 per 1M tokens.
Model Details
ID
nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B
Provider
CrusoeFamily
nemotron
Release Date
Apr 28, 2026
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
CRUSOE_API_KEY
API Base URL
https://api.inference.crusoecloud.com/v1