← Back to catalog
Provider Docs
Llama-3.1-Nemotron-Ultra-253B-v1
llamaNvidia · nvidia/llama-3.1-nemotron-ultra-253b-v1
Capabilities
Tool CallYes
ReasoningYes
Structured OutputNo
Temperature ControlYes
AttachmentsNo
Open WeightsNo
Modalities
Input
text
Output
text
Pricing (per 1M tokens)
Input$0.000
Output$0.000
Direct installation coming soon — March 2026
Details
ProviderNvidia
Model IDnvidia/llama-3.1-nemotron-ultra-253b-v1
Familyllama
Knowledge Cutoff2024-07
Release Date2024-07-01
Last Updated2025-09-05
Limits
Context131K
Max Output8K
SDK
@ai-sdk/openai-compatible