AI Hub
All models
LLM

Llama Nemotron Super 49B v1.5

NVIDIA

Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type
LLM
Released
July 25, 2025
Output speed
51 tok/s
Latency (TTFT)
0.29s
API pricing
$0.10 in · $0.40 out / 1M tokens

Benchmarks

Reasoning

Coding

Math

Compare Llama Nemotron Super 49B v1.5 with

See all Llama Nemotron Super 49B v1.5 alternatives →