- How accurate is Nemotron 3 Ultra?
- Nemotron 3 Ultra answered 48 of 80 questions correctly (60.0%) in our 2026-10-27 run, ranking #38 of 78 models.
- How fast is Nemotron 3 Ultra?
- Nemotron 3 Ultra generated a median of 136 output tokens per second in our 2026-10-27 run, ranking #21 of 78. Median time to first token was 0.8 s.
- What is the latency of Nemotron 3 Ultra?
- Nemotron 3 Ultra had a median time to first token of 0.8 s in our 2026-10-27 run, ranking #41 of 78 models.
- How much does Nemotron 3 Ultra cost?
- Nemotron 3 Ultra cost $0.0057 per question on average as billed in our 2026-10-27 run, reasoning tokens included.
- What is Nemotron 3 Ultra API pricing?
- Nemotron 3 Ultra is listed at $0.6 per million input tokens and $2.4 per million output tokens on OpenRouter.
- What is the context window of Nemotron 3 Ultra?
- Nemotron 3 Ultra accepts up to 262,144 tokens of context, according to OpenRouter's model catalogue.
- Is Nemotron 3 Ultra open source?
- Yes. Nemotron 3 Ultra is an open-weights model: NVIDIA publishes the weights, so you can run it yourself as well as through an API.
- Who makes Nemotron 3 Ultra?
- Nemotron 3 Ultra is made by NVIDIA. We tested it through OpenRouter using the model ID nvidia/nemotron-3-ultra-550b-a55b.
- Where can I use Nemotron 3 Ultra via API?
- Through OpenRouter, Nemotron 3 Ultra is served by 3 hosts: BaseTen, DeepInfra, Venice.