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...
Anyone in the Space can @-mention NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 with the team's shared context — pooled credits, one chat, one memory.
Starter is free forever — 1 Space, 100 credits/month, 1 MCP. No card.
Specifications
- Provider
- nvidia
- Category
- llm
- Context length
- 131,072 tokens
- Max output
- 16,384 tokens
- Modalities
- text
- License
- proprietary
- Released
- 2025-10-10
Pricing
- Input
- $0.10/Mtok
- Output
- $0.40/Mtok
- Model ID
nvidia/llama-3.3-nemotron-super-49b-v1.5
Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool — one plan, one balance for everyone.
Team cost calculator
5 seats · 80 msgs/day
Switchy meters this against your org's shared credit pool — one plan, one balance for everyone.
Providers
| Provider | Context | Input | Output | P50 latency | Throughput | 30d uptime |
|---|---|---|---|---|---|---|
| nvidia | 131k | $0.10/Mtok | $0.40/Mtok | — | — | — |
Performance
Benchmarks
Works well with
Top MCPs
Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.