Llama Nemotron Super 49B v1.5 (Non-reasoning)
Intelligence
14.6
#350/523
Coding
10.5
#330/429
Math
8
#235/265
Speed
61 tok/s
TTFT: 383.00s
Pricing
$0.10 / $0.40
per 1M tokens (in/out)
Llama Nemotron Super 49B v1.5 (Non-reasoning) is NVIDIA’s latest model designed for high-speed processing tasks. It operates at 61.142 tokens per second and is priced at $0.1 per million input tokens and $0.4 per million output tokens, targeting professional users in data-intensive environments.
When to Use Llama Nemotron Super 49B v1.5 (Non-reasoning)
✓ Best For
- High-speed data processing
- Token-based applications
- Professional coding tasks
✗ Not Ideal For
- Complex mathematical computations
- Reasoning-based applications
How Llama Nemotron Super 49B v1.5 (Non-reasoning) Compares
Intelligence Index · Higher is better
AlibabaGoogleNVIDIAMetaOpenAI
Benchmark Profile
Coding Index
InclusionAIUpstageNVIDIAMBZUAI Institute of Foundation ModelsAllen Institute for AI
Output Speed · tok/s
AnthropicMetaNVIDIAAlibaba
Math Index
GoogleLiquid AINVIDIAMeta
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (15)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 14.6 | |
| Coding Index | 10.5 | |
| Math Index | 8 | |
| MMLU-Pro | 692% | |
| GPQA | 481% | |
| LiveCodeBench | 29% | |
| HLE | 43% | |
| SciCode | 23.8% | |
| IFBench | 32.9% | |
| LCR | 22% | |
| TerminalBench Hard | 3.8% | |
| Tau2 | 25.1% | |
| AIME | 13.7% | |
| AIME 2025 | 8% | |
| MATH 500 | 77% |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Llama Nemotron Super 49B v1.5 (Non-reasoning) released?
Llama Nemotron Super 49B v1.5 (Non-reasoning) was released on July 25, 2025.
Who created Llama Nemotron Super 49B v1.5 (Non-reasoning)?
Llama Nemotron Super 49B v1.5 (Non-reasoning) was created by NVIDIA.
How intelligent is Llama Nemotron Super 49B v1.5 (Non-reasoning)?
Llama Nemotron Super 49B v1.5 (Non-reasoning) scores 15 on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 13).
How fast is Llama Nemotron Super 49B v1.5 (Non-reasoning)?
Llama Nemotron Super 49B v1.5 (Non-reasoning) generates output at 54.5 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight non-reasoning models of similar size (median: 60.2 t/s).
What is the latency of Llama Nemotron Super 49B v1.5 (Non-reasoning)?
Llama Nemotron Super 49B v1.5 (Non-reasoning) has a time to first token (TTFT) of 1.49s (based on the median across providers serving the model), which is better than average compared to other open weight non-reasoning models of similar size (median: 1.90s).
How much does Llama Nemotron Super 49B v1.5 (Non-reasoning) cost?
Llama Nemotron Super 49B v1.5 (Non-reasoning) costs $0.10 per 1M input tokens (very competitive, median: $0.54) and $0.40 per 1M output tokens (very competitive, median: $0.90), based on the median across providers serving the model.
What is Llama Nemotron Super 49B v1.5 (Non-reasoning) API pricing?
Llama Nemotron Super 49B v1.5 (Non-reasoning) costs $0.10 per 1M input tokens and $0.40 per 1M output tokens (based on the median across providers serving the model). For a blended rate (3:1 input to output ratio), this is $0.17 per 1M tokens. Pricing may vary by provider.
How verbose is Llama Nemotron Super 49B v1.5 (Non-reasoning)?
When evaluated on the Intelligence Index, Llama Nemotron Super 49B v1.5 (Non-reasoning) generated 6.5M output tokens, which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 6.4M).
Is Llama Nemotron Super 49B v1.5 (Non-reasoning) a reasoning model?
No, Llama Nemotron Super 49B v1.5 (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Llama Nemotron Super 49B v1.5 (Non-reasoning) support?
Llama Nemotron Super 49B v1.5 (Non-reasoning) supports text input.
What output modalities does Llama Nemotron Super 49B v1.5 (Non-reasoning) support?
Llama Nemotron Super 49B v1.5 (Non-reasoning) supports text output.
Can Llama Nemotron Super 49B v1.5 (Non-reasoning) process images?
No, Llama Nemotron Super 49B v1.5 (Non-reasoning) does not support image input. It can only process text.
Is Llama Nemotron Super 49B v1.5 (Non-reasoning) multimodal?
No, Llama Nemotron Super 49B v1.5 (Non-reasoning) is not multimodal. It only supports text input.
What is the context window of Llama Nemotron Super 49B v1.5 (Non-reasoning)?
Llama Nemotron Super 49B v1.5 (Non-reasoning) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Is Llama Nemotron Super 49B v1.5 (Non-reasoning) open source?
Yes, Llama Nemotron Super 49B v1.5 (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
