Llama 3.3 Nemotron Super 49B V1.5 API Pricing 2026

Overview

Llama 3.3 Nemotron Super 49B V1.5 was released on October 10, 2025. Pricing starts at $0.100 per million input tokens and $0.400 per million output tokens. The model supports a context window of up to 131K tokens. API access is available through Nvidia.

Context Window

131K

tokens

Pricing

Input$0.100

Output$0.400

per 1M tokens

Speed

Output69 tok/s

TTFT0.22s

median latency

Capabilities

Tools

Pricing Comparison

Compare Llama 3.3 Nemotron Super 49B V1.5 with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Provider	Model	Input $/M	Output $/M	Context	Actions
M Nvidia	llama-3.3-nemotron-super-49b-v1.5	$0.100	$0.400	131,072	Try
QW Qwen	qwen3-vl-8b-instruct	$0.080	$0.500	131,072	Try
A Alibaba	tongyi-deepresearch-30b-a3b	$0.090	$0.400	131,072	Try
QW Qwen	qwen3-next-80b-a3b-instruct	$0.090	$1.100	262,144	Try
NS Neversleep	llama-3.1-lumimaid-8b	$0.090	$0.600	32,768	Try
BY Bytedance	ui-tars-1.5-7b	$0.100	$0.200	128,000	Try
G Google	gemini-2.5-flash-lite-preview-09-2025	$0.100	$0.400	1,048,576	Try
A Allenai	olmo-3-7b-instruct	$0.100	$0.200	65,536	Try
MI Mistral AI	voxtral-small-24b-2507	$0.100	$0.300	32,000	Try
MI Mistral AI	mistral-small-creative	$0.100	$0.300	32,768	Try
MI Mistral AI	ministral-3b-2512	$0.100	$0.100	131,072	Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Llama 3.3 Nemotron Super 49B V1.5 is available from multiple providers with different pricing and availability.

2

Providers

$0.100

Cheapest Input/M

$0.400

Cheapest Output/M

OpenRouter

Best Price

Provider Pricing

2 models

Provider	Input $/M	Output $/M	Uptime
OpenRouter Best Price	$0.100	$0.400	-
D DeepInfra Best Price	$0.100	$0.400	100.0%

Provider pricing data sourced from OpenRouter and Helicone

Cost vs. Quality

Compare Llama 3.3 Nemotron Super 49B V1.5's benchmark performance against all models.

X-axis:

Y-axis:

Loading chart...

Llama 3.3 Nemotron Super 49B V1.5

Other models

Detailed Benchmark Scores

Intelligence

15.1 (38th pct)

Coding

10.3 (20th pct)

Math

8.0 (13th pct)

MMLU Pro

69.2 (39th pct)

GPQA

48.1 (36th pct)

LiveCodeBench

29.0 (33th pct)

AIME

13.7 (32th pct)

Aider

-

Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try Llama 3.3 Nemotron Super 49B V1.5

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Llama 3.3 Nemotron Super 49B V1.5 directly in your browser.

Open Playground