Nvidia: Llama 3.3 Nemotron Super 49B V1.5
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... 49B parameters derived from Llama 3.3 70B with post-training Optimized for agentic workflows: RAG, tool calling, code 128K context window for complex multi-step tasks Competitive pricing at $0.40/$0.40 per 1M tokens Strong across math, code, science, and instruction following Derivative model: not trained from scratch by NVIDIA Only moderately improved over base Llama 3.3 70B English-centric; limited multilingual performance Agentic applications requiring tool calling RAG pipelines and knowledge retrieval Enterprise chat and instruction following Code generation and technical tasks
Specifications
| Lab | Nvidia |
|---|---|
| Context window | 131,072 |
| Input price | $0.40/1M |
| Output price | $0.40/1M |
| Release | 2025-10-01 00:00:00 |
Strengths
- 49B parameters derived from Llama 3.3 70B with post-training
- Optimized for agentic workflows: RAG, tool calling, code
- 128K context window for complex multi-step tasks
- Competitive pricing at $0.40/$0.40 per 1M tokens
- Strong across math, code, science, and instruction following
Weaknesses
- Derivative model: not trained from scratch by NVIDIA
- Only moderately improved over base Llama 3.3 70B
- English-centric; limited multilingual performance
Best for
- Agentic applications requiring tool calling
- RAG pipelines and knowledge retrieval
- Enterprise chat and instruction following
- Code generation and technical tasks
In Depth: Llama 3.3 Nemotron Super 49B V1.5
Summary
Llama 3.3 Nemotron Super 49B V1.5 is an AI model from Nvidia.
Released 2025-10-01 00:00:00. It currently appears in the Overall category on LMRank. It supports Text input and produces Text output, with a context window of 131.1K tokens. Input pricing is $0.40 per 1M tokens and output is $0.40 per 1M tokens on OpenRouter.