NVIDIA

Llama 3.3 Nemotron Super 49b V1.5

nvidia/llama-3.3-nemotron-super-49b-v1.5

131.1K context·16.4K max output·text->text

Input

$0.1000

per 1M tokens

Output

$0.4000

per 1M tokens

Cache Read

-

not available

Cache Write

-

not available

Quality Benchmarks

FrontierValue: Infinity

Coding

Code generation, completion, debugging

70.2

Math

Competition math, calculus, olympiad

70.2

Reasoning

Logic, spatial, puzzle solving

70.2

Language

Summarization, paraphrase, writing

70.2

Overall

70.2

Source: LiveBench (livebench.ai) / Scores 0-100

Capabilities

VisionTool UseReasoningPrompt Caching

Similar Price Range

More from NVIDIA

Deploy your AI agent for $33/mo flat.

Managed Telegram bot hosting. We handle the infrastructure.

Any model. Any channel. Zero infrastructure.