Model · NVIDIA

Llama Nemotron Super 49B

Single-H100 reasoning model with toggleable think-mode and vendor-reported AIME scores.

Pricing

Model Overview

Tracked token-pricing fields for this model family. Empty pricing fields stay hidden until the source publishes them.

Model pricing
Price field	Value
Input	$0.20 / 1M tokens
Output	$0.60 / 1M tokens
Source	Llama Nemotron Super 49B pricing
Verified	Apr 5, 2026 (High)

Surface

Input and output modalities, enabled feature flags, strengths, and tradeoffs.

Model capabilities
Attribute	Values
Modalities	text to text
Capabilities	reasoningbatchSupportpromptCachingfunctionCallingstructuredOutputs
Strengths	Fits single H100, Vendor-reported AIME score for 50B class, Toggleable reasoning
Tradeoffs	Text-only, requires NIM API or own GPU

References

Canonical launch, documentation, pricing, and release-note URLs.

Official model links
Reference	URL
Intro	https://developer.nvidia.com/blog/introducing-llama-3-3-nemotron-super-49b/
Docs	https://developer.nvidia.com/nemotron
Pricing	https://build.nvidia.com/explore/discover
Release note	https://developer.nvidia.com/blog/

Coverage

Reported benchmark families, versions, scores, sources, and notes.

Benchmark coverage
Benchmark	Version	Score	Date	Source	Notes
GPQA	2024	66.67 %	Mar 1, 2025	NVIDIA	Vendor-reported
AIME 2025	2025	82.71 %	Mar 1, 2025	NVIDIA	Vendor-reported, v1.5
MATH-500	2024	97.4 %	Mar 1, 2025	NVIDIA	Vendor-reported, v1.5

Lifecycle

Lifecycle transitions and release timeline for this model family.

Release history
Release	Alias	Lifecycle	Release Date	Deprecation	Shutdown	Summary
Llama Nemotron Super 49B	nemotron-super-49b	Active	Mar 18, 2025	—	—	Current published model family snapshot.

Surfaces

Provider-specific hosting, context, pricing notes, feature differences, and provider-status context.

Host coverage
Host	Type	Context	Pricing Note	Differences
NVIDIA NIM	first-party	128.0K	$0.20/$0.60 per MTok.	Thinking mode toggle

Migration

Documented migration summary, successor families, and known breaking changes.

Migration guidance
Topic	Details
Summary	Nemotron option for single-GPU deployments. Use Ultra for larger-model depth.
Replacement models	nemotron-ultra-253b

Timeline

Cataloged model-family updates and source references.

Change events
Date	Type	Title	Description	Source
Mar 18, 2025	family_added	Llama Nemotron Super 49B published	Initial public model family launch.	Llama Nemotron Super 49B release notes

From NVIDIA