Llama-3.3-Nemotron-Super-49B-v1.5

Name: Llama-3.3-Nemotron-Super-49B-v1.5
Author: DeepInfra

49B

Llama-3.3-Nemotron-Super-49B-v1.5 is a large language model (LLM) optimized for advanced reasoning, conversational interactions, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta's Llama-3.3-70B-Instruct, it employs a Neural Architecture Search (NAS) approach, significantly enhancing efficiency and reducing memory requirements.

Context

131K

Input price

$0.4/1M tokens

Output price

$0.4/1M tokens

Capabilities

Show unsupported (3)

Reasoning & Interaction

Reasoning

Tool Calling

Output Control

Structured Output

JSON Mode

Infrastructure

Streaming

Details

Model IDnvidia/Llama-3.3-Nemotron-Super-49B-v1.5

ProviderDeepInfra

CreatorNVIDIA

FamilyLlama-3.3

License—

Statusactive

Typechat

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters49B

Architecture—

Context window131K tokens

Max input—

Max output—

Reasoning tokensYes

Knowledge cutoff—

Release date—

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

Endpoints

Chat CompletionsPOST

Generate chat responses with messageshttps://api.deepinfra.com/v1/openai/v1/chat/completions

Pricing

Input

$0.4

Output

$0.4

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: Llama-3.3

Model	Caps	Perf	Speed	Context	Max out	Pricing
Llama-3.3-70B-Instruct-Turbo	TJJMSF	—	—	131K	—	$0.1$0.32
Llama-3.3-Nemotron-Super-49B-v1.5	RTJJMS	—	—	131K	—	$0.4$0.4

API

GET/v1/models/deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5