NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
🇺🇸 NVIDIA · Llama 3.3
Input Price $0.100 per million tokens NT$3.2
Output Price $0.400 per million tokens NT$12.8
Context Window 131K tokens Output limit: 16K
OpenRouter Route Price Please verify with official pricing pages
| Dimension | Unit | Price (USD) |
|---|---|---|
| Input | per 1M tokens | $0.100 |
| Output | per 1M tokens | $0.400 |
- Provider
- NVIDIA (NVIDIA)
- Model Family
- Llama 3.3
- Version String
- nvidia/llama-3.3-nemotron-super-49b-v1.5
- Status
- active
- Modality
- text
- Context Window
- 131,072 tokens
- Output Limit
- 16,384 tokens
Index Metrics
Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis
Agentic Index 9 F Measured: 2026-05-27
Coding Index 15 D Measured: 2026-05-27
Intelligence Index 19 D Measured: 2026-05-27
Benchmark Scores
Data source: Artificial Analysis
AA-LCR 34.0% D Measured: 2026-05-27
GPQA Diamond 74.9% B Measured: 2026-05-27
HLE 6.8% D Measured: 2026-05-27
IFBench 37.0% D Measured: 2026-05-27
Non-Hallucination 24.5% Measured: 2026-05-27
Omniscience Accuracy 16.9% Measured: 2026-05-27
SciCode 34.8% B Measured: 2026-05-27
Tau2 28.1% Measured: 2026-05-27
TerminalBench 5.3% Measured: 2026-05-27
Performance Metrics
Real-world benchmarks, updated every 72 hours by Artificial Analysis — Artificial Analysis
First Token Latency 1.3s Measured: 2026-05-27
Output Speed 48 t/s Measured: 2026-05-27
Response Time 53.0s Measured: 2026-05-27
90-Day Price Trend
Input / Output price (USD per 1M tokens)
Past 90 days of records; every price change is shown here
| Date | Dimension | Price (USD) | Source |
|---|---|---|---|
| 2026-05-27 | Output | $0.400 | openrouter |
| 2026-05-27 | Input | $0.100 | openrouter |
| 2026-05-26 | Output | $0.400 | openrouter |
| 2026-05-26 | Input | $0.100 | openrouter |
| 2026-05-25 | Output | $0.400 | openrouter |
| 2026-05-25 | Input | $0.100 | openrouter |
| 2026-05-24 | Output | $0.400 | openrouter |
| 2026-05-24 | Input | $0.100 | openrouter |
| 2026-05-23 | Output | $0.400 | openrouter |
| 2026-05-23 | Input | $0.100 | openrouter |
| 2026-05-22 | Output | $0.400 | openrouter |
| 2026-05-22 | Input | $0.100 | openrouter |
| 2026-05-22 | Output | $0.400 | openrouter |
| 2026-05-22 | Input | $0.100 | openrouter |
| 2026-05-21 | Output | $0.400 | openrouter |
| 2026-05-21 | Input | $0.100 | openrouter |
| 2026-05-20 | Output | $0.400 | openrouter |
| 2026-05-20 | Input | $0.100 | openrouter |
| 2026-05-19 | Output | $0.400 | openrouter |
| 2026-05-19 | Input | $0.100 | openrouter |
| 2026-05-18 | Output | $0.400 | openrouter |
| 2026-05-18 | Input | $0.100 | openrouter |
| 2026-05-17 | Output | $0.400 | openrouter |
| 2026-05-17 | Input | $0.100 | openrouter |
| 2026-05-16 | Output | $0.400 | openrouter |
| 2026-05-16 | Input | $0.100 | openrouter |
| 2026-05-16 | Output | $0.400 | openrouter |
| 2026-05-16 | Input | $0.100 | openrouter |
| 2026-05-16 | Output | $0.400 | openrouter |
| 2026-05-16 | Input | $0.100 | openrouter |
| 2026-05-16 | Output | $0.400 | openrouter |
| 2026-05-16 | Input | $0.100 | openrouter |
| 2026-05-15 | Output | $0.400 | openrouter |
| 2026-05-15 | Input | $0.100 | openrouter |
| 2026-05-14 | Output | $0.400 | openrouter |
| 2026-05-14 | Input | $0.100 | openrouter |
| 2026-05-13 | Output | $0.400 | openrouter |
| 2026-05-13 | Input | $0.100 | openrouter |
| 2026-05-12 | Output | $0.400 | openrouter |
| 2026-05-12 | Input | $0.100 | openrouter |
| 2026-05-11 | Output | $0.400 | openrouter |
| 2026-05-11 | Input | $0.100 | openrouter |
| 2026-05-10 | Output | $0.400 | openrouter |
| 2026-05-10 | Input | $0.100 | openrouter |
| 2026-05-10 | Output | $0.400 | openrouter |
| 2026-05-10 | Input | $0.100 | openrouter |
| 2026-05-09 | Output | $0.400 | openrouter |
| 2026-05-09 | Input | $0.100 | openrouter |
| 2026-05-09 | Output | $0.400 | openrouter |
| 2026-05-09 | Input | $0.100 | openrouter |
Description
Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and...
Key Insights
Key data points from this page for quick reference and citation.
- NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 Input price: $0.1/M tokens
- NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 Output price: $0.4/M tokens
- Context window: 131,072 tokens
- Provider: NVIDIA
- Model family: Llama 3.3
- Modalities: text
- Data source: OpenRouter, updated daily