nemotron-3-ultra-550b-a55b
NVIDIA/Open weights/2 providers
NVIDIA Nemotron 3 Ultra is an open frontier reasoning and orchestration model with 55B active parameters out of 550B total (hybrid Transformer-Mamba MoE). Text input/output with up to 1M context, built for long-running agentic workflows: agent orchestration, coding agents, deep research, and complex enterprise tasks. Strong at multi-step reasoning and planning with high-throughput inference. Part of the NVIDIA Nemotron family.MoreLess
Which id to call
nemotron-3-ultra-550b-a55bRequesty routes this id across every provider serving nemotron-3-ultra-550b-a55b, picking on price and health and failing over automatically. The id stays valid when a provider changes underneath it.
From /1M input
free
NVIDIA
Context
1.0M
66K output
Best first token
2.23s
Nebius AI
Regions
1
293 tok/s best
Capabilities 3/8
46/s↑ 6/s
Week of Sep 28, latest, median of 2 providers
Median tokens per second once generation starts, measured on traffic routed through Requesty through Oct 3. Hover a week to read it.moreless
Each provider line is that provider's own median across every model it serves, which is the grain published per provider, so a provider line can cover weeks this model was not called in yet. The exact per-provider figures for this model are ranked below.
2 endpoints / 1 region
Providers serving nemotron-3-ultra-550b-a55b
Provider prices, per 1M tokens. Pay as you go adds 5%, or 0% on your own keys.moreless
The two panes rank nemotron-3-ultra-550b-a55b as measured on Requesty traffic: by the provider that served it, and by the region the request came from, where the share is how much of that region's traffic this model carries. Whole-window figures, because that is the grain Requesty publishes per provider and per region.
By provider
By traffic region
Median tokens per second once generation starts. Bar length is the value, so the longest bar wins.moreless
Whole-window figures as published, not an average of weekly points.
A column is blank where no qualifying sample exists, and every row links to that provider's endpoint page.
model=
Which id to call
One base url, https://router.requesty.ai/v1, and one key for every id here.
nemotron-3-ultra-550b-a55bRequesty routes this id across every provider serving nemotron-3-ultra-550b-a55b, picking on price and health and failing over automatically. The id stays valid when a provider changes underneath it.
OpenAI compatible
Call it in three lines
Change the base url, use your Requesty key, set the model to any id on the left. Existing OpenAI SDK code needs no other edit.
123456789101112131415from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1", ) response = client.chat.completions.create( model="nemotron-3-ultra-550b-a55b", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ], ) print(response.choices[0].message.content)
Artificial Analysis
Benchmark scores
Artificial Analysis Coding Index: a composite of coding evaluations including LiveCodeBench, SciCode and Terminal-Bench.
Graduate-level physics, chemistry & biology questions designed to resist Googling.
Artificial Analysis Intelligence Index: a composite of multiple evaluations measuring overall model capability.
Scores from artificialanalysis.ai. They measure the model, not the provider, so they are the same on every endpoint above.
6
More from NVIDIA
nemotron-lightning-3.5-30b-a3b
262K ctx/from $0.05/1 provider
nemotron-3.5-lightning-30b-a3b
1.0M ctx/from free/1 provider
nvidia-nemotron-3-ultra
262K ctx/from $0.37/1 provider
nemotron-3.5-content-safety
131K ctx/from free/1 provider
nemotron-3-ultra-nvfp4
262K ctx/from $0.60/1 provider
nemotron-3-nano-omni-30b-a3b-reasoning
131K ctx/from free/1 provider
Reference
nemotron-3-ultra-550b-a55b questions
Which providers serve nemotron-3-ultra-550b-a55b?
nemotron-3-ultra-550b-a55b is available from 2 providers through Requesty: NVIDIA, Nebius AI. All endpoints share one OpenAI-compatible API and one key, and Requesty fails over between them automatically.
How much does nemotron-3-ultra-550b-a55b cost?
Pricing starts at free per million input tokens and free per million output tokens on NVIDIA, the cheapest endpoint. Prices vary by provider and region; the table above shows every endpoint. Those are the upstream provider rates: pay as you go adds 5% on top, or 0% if you bring your own provider keys.
Is nemotron-3-ultra-550b-a55b open weights?
Yes. nemotron-3-ultra-550b-a55b is an open-weights model from NVIDIA, which is why multiple inference providers can host it. Provider choice affects price, latency, and data-privacy terms, all compared above.
What is the context window of nemotron-3-ultra-550b-a55b?
nemotron-3-ultra-550b-a55b supports up to 1.0M tokens of context, with up to 66K output tokens per response. Some providers expose a smaller window; check the per-endpoint context column above.
Which provider is fastest for nemotron-3-ultra-550b-a55b?
In recent production traffic through Requesty, Nebius AI had the lowest median time to first token (2.23s) for nemotron-3-ultra-550b-a55b. Latency shifts over time, so Requesty's latency-based routing picks the fastest healthy provider per request automatically.
How do I use nemotron-3-ultra-550b-a55b with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "nemotron-3-ultra-550b-a55b" or any endpoint id from the table above. The quickstart section shows Python, JavaScript and cURL snippets.
Should I call nemotron-3-ultra-550b-a55b by its managed id or a provider id?
Use the managed id, "nemotron-3-ultra-550b-a55b". Requesty picks which of the 2 providers serves each request based on price and health, and fails over when one degrades, so the id keeps working while the routing changes underneath it. Send a provider id like "nvidia/nemotron-3-ultra-550b-a55b" only when you need one specific deployment and want no failover.
Route nemotron-3-ultra-550b-a55b through one endpoint
One key for 2 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in.