All Models

nvidia-nemotron-3-ultra

nemotron Reasoning Tool Calling Open Weights Structured Output

NVIDIA Nemotron 3 Ultra is NVIDIA's strongest open-weights reasoning model, positioned near GPT-5.4 Mini (xhigh) and ahead of DeepSeek V4-Flash and Qwen3.5-397B-A17B.

Providers 2
Released Jun 4, 2026
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

38.3
Intelligence Index
49.3
Coding Index

Available Providers (2)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Requesty nvidia-nemotron-3-ultra $0.45/MTok $2.25/MTok 262.1K 131.1K
Venice AI nvidia-nemotron-3-ultra-550b-a55b $0.63/MTok $3.13/MTok 256K 32.8K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output