NVIDIA: Llama 3.3 Nemotron Super 49B V1.5nvidia
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5: $0.40/1M input, $0.40/1M output, 131K context. 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...
API Pricing (per 1M tokens)
| Input | $0.40 |
| Output | $0.40 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.40 |
Specs & Performance
| Context Length | 131K |
| Max Output | 16K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
More from nvidia
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 API cost?
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 costs $0.40/1M input tokens and $0.40/1M output tokens. Blended cost at a 3:1 ratio is about $0.40/1M 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 supports a 131K token context window with up to 16K output tokens.
Is NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 worth it?
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.