NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
Analysis Summary
NVIDIA's Llama 3.3 Nemotron Super 49B V1.5 is a fine-tuned 49B parameter model optimised for reasoning-heavy tasks. Its math index of 54.7 and GPQA score of 0.643 are strong for its size class, and the inclusion of tool use and function calling makes it viable for structured business workflows. Pricing at $0.40/1M for both input and output is competitive for a model of this capability tier.
For businesses, it suits mid-complexity analytical tasks, structured data extraction, and lightweight agentic pipelines where cost efficiency matters. The agentic index of 26.9 is modest, so it is not a first choice for complex multi-step autonomous agents. The 131K context window is adequate for most document-level tasks.
At $0.40/1M, it offers reasonable value for teams that need reliable reasoning without flagship pricing. Best suited to organisations comfortable deploying NVIDIA-hosted inference for analytical or tool-augmented workflows.
Assessed June 30, 2026
Editorial notes
NVIDIA's Llama 3.3 Nemotron Super 49B V1.5 delivers strong math and GPQA performance for a 49B model, with tool use and function calling support at a very competitive $0.40/1M price point.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 compares
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 ranks #207 of 387 AI models we track for overall intelligence, #158 of 294 for agentic tasks. Its 131K-token context window is larger than 58% of the models we list. At $0.40 per million input tokens it is cheaper than 39% of comparable models.
About 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 Metaās Llama-3.3-70B-Instruct with a 128K context. Itās post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 stack up?
Compare side-by-side with other efficient models.
Model Information
| OpenRouter ID |
nvidia/llama-3.3-nemotron-super-49b-v1.5
|
| Provider | nvidia |
| Release Date | October 10, 2025 |
| Context Length | 131,072 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.40 | $0.000400 |
| Output | $0.40 | $0.000400 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
How much does NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 cost?
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 costs $0.40 per million input tokens and $0.40 per million output tokens.
What is the context window of NVIDIA: Llama 3.3 Nemotron Super 49B V1.5?
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 has a context window of 131,072 tokens (131K).
What can NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 do?
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 supports tool use and function calling.
Who created NVIDIA: Llama 3.3 Nemotron Super 49B V1.5?
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 is developed by NVIDIA and was released on October 10, 2025.
