Question 1

What is Nemotron 3 Ultra 550B A55B?

Accepted Answer

Nemotron 3 Ultra 550B A55B is a model from NVIDIA, released on Jun 4, 2026. NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks. It is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.

Question 2

How much does Nemotron 3 Ultra 550B A55B cost?

Accepted Answer

On the Respan gateway, input starts at $0.25 per 1M tokens on Perplexity, and output starts at $2.20 per 1M tokens on DeepInfra and OpenRouter, after gateway discounts. Averaged across 7 providers, it costs $0.58 per 1M input tokens and $2.61 per 1M output tokens.

Question 3

Which providers serve Nemotron 3 Ultra 550B A55B on Respan?

Accepted Answer

7 providers serve Nemotron 3 Ultra 550B A55B: Perplexity, DeepInfra, OpenRouter, Baseten, Fireworks, TogetherAI, and 1 more. Perplexity, Fireworks, and TogetherAI require your own provider API key (BYOK).

Question 4

What is Nemotron 3 Ultra 550B A55B's context window?

Accepted Answer

Nemotron 3 Ultra 550B A55B accepts up to 1.0M tokens of context on its largest provider route.

Question 5

How do I use Nemotron 3 Ultra 550B A55B with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "nemotron-3-ultra-550b-a55b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Nemotron 3 Ultra 550B A55B?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 61 tokens per second, and the lowest response latency was 0.7 seconds on Baseten. Speed varies with request size and provider.

Question 7

Where does Nemotron 3 Ultra 550B A55B rank on the Respan Index?

Accepted Answer

Nemotron 3 Ultra 550B A55B scores 26.0 out of 100 on the Respan Index v1.1, ranking #75 of 138 models. By category: Coding 6.9, Agents 29.7, Reasoning 22.8, Knowledge & language 35.4, and Human preference 50.6. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does Nemotron 3 Ultra 550B A55B score on benchmarks?

Accepted Answer

Nemotron 3 Ultra 550B A55B has 21 published benchmark scores, including LiveBench Coding 70.7%, BrowseComp 41.4%, and GPQA Diamond 87.9%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
PerplexityBYOK only`perplexity/nemotron-3-ultra-550b-a55b`	262K	$0.25/M	$2.50/M
DeepInfra`deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B`	262K	$0.50/M	$2.20/M
OpenRouter`openrouter/nvidia/nemotron-3-ultra-550b-a55b`	262K	$0.50/M	$2.20/M
Baseten`baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B`	203K	$0.60/M	$2.40/M
FireworksBYOK only`fireworks_ai/nemotron-3-ultra-nvfp4`	262K	$0.60/M	$2.40/M
TogetherAIBYOK only`together_ai/nvidia/nemotron-3-ultra-550b-a55b`	512K	$0.60/M	$3.60/M
Nebius`nebius/nvidia/Nemotron-3-Ultra-550b-a55b`	1.0M	$1.00/M	$3.00/M

Nemotron 3 Ultra 550B A55B

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Indexv1.1

Coding4

Apps