Search models/
Models / NVIDIA / Nemotron 3 Ultra

Nemotron 3 Ultra APITESTEDOPEN WEIGHTS1M context

by NVIDIA · text->text · released 2026-06-04

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

Get an API key Try in Chat https://api.datallmlab.com/v1
Input / 1M
$0.50
Output / 1M
$2.20
Context
1M
Our coding score
8/9

Pricing & specs mirror our live pricing as of July 2026 (pay-as-you-go). Coding score is our own measured result.

✅ First-party tested — we ran Nemotron 3 Ultra on our 9-task coding suite

Score
8/9
Cost / 1k tasks
Free
Avg latency
48.2s
Reasoning tokens
9,136

tested on free tier. Executed against hidden tests at real billed cost — full results · how we test.

What is Nemotron 3 Ultra?

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...

Nemotron 3 Ultra on the release timeline

$0.20$0.66$2.20Nemotron 3 Ultra · $2.202025-122026-032026-06
Each point is a nemotron release, placed at its launch date with its current output price (log scale, $/1M). Bubble size ∝ context window; Nemotron 3 Ultra is highlighted. Source: provider catalog, verified July 2026.

Nemotron 3 Ultra pricing

Pay-as-you-go on DataLLM Lab — these are our live list prices (identical to the pricing page):

ModelInput / 1MOutput / 1MCache readCache writeContext
Nemotron 3 Ultra$0.50$2.20$0.101M

On output price, Nemotron 3 Ultra is cheaper than 40% of the 309 models in the catalog.

What Nemotron 3 Ultra costs per month

WorkloadTokens in / out (monthly)Est. cost
Support chatbot40M / 12M$46.40
RAG / knowledge base200M / 20M$144
Coding agent80M / 25M$95.00
Batch extraction150M / 8M$92.60
Content generation20M / 40M$98.00

Estimate your own monthly cost

= input × $0.50 + output × $2.20 per 1M · pay-as-you-go, computed in your browser.

Cost = input price × input volume + output price × output volume. The same five workloads run on every model page, so any two compare directly.

Nemotron 3 Ultra vs alternatives

Pick Nemotron 3 Ultra when you want its tested 8/9 coding score or the 1M context. If price is the only priority, Nemotron 3 Nano 30B A3B is cheaper per token.
ModelInput / 1MOutput / 1MContextOur test
Nemotron 3 Ultra$0.50$2.201M8/9
Llama 3.3 Nemotron Super 49B V1.5$0.40$0.40131K
Nemotron 3 Super$0.08$0.401M
Nemotron 3 Nano 30B A3B$0.05$0.20262K
MiniMax M1$0.40$2.201M
GLM 4.5$0.60$2.20131K

When not to use Nemotron 3 Ultra

Specs

Model IDnvidia/nemotron-3-ultra-550b-a55b
Modalitytext->text (input: text)
Context window1,000,000 tokens
Max output16,384 tokens
Tool / function calling✅ Yes
Structured output (JSON)✅ Yes
Released2026-06-04
Open weightsnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

How to call Nemotron 3 Ultra

from openai import OpenAI
client = OpenAI(base_url="https://api.datallmlab.com/v1", api_key="YOUR_DATALLM_LAB_KEY")
resp = client.chat.completions.create(
    model="nvidia/nemotron-3-ultra-550b-a55b",
    messages=[{"role": "user", "content": "Hello"}],
    # supports tools=[...] and tool_choice
)
print(resp.choices[0].message.content)
curl https://api.datallmlab.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nvidia/nemotron-3-ultra-550b-a55b","messages":[{"role":"user","content":"Hello"}]}'
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.datallmlab.com/v1", apiKey: process.env.DATALLM_KEY });
const r = await client.chat.completions.create({
  model: "nvidia/nemotron-3-ultra-550b-a55b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(r.choices[0].message.content);

The same key routes Nemotron 3 Ultra and 300+ other models — switch models by changing one string. How OpenAI-compatible APIs work.

Prompting tips for Nemotron 3 Ultra

Tips are derived from Nemotron 3 Ultra's actual capabilities — context window, tool & JSON support, modality and price tier — not generic advice.

Open-source tools for Nemotron 3 Ultra

Popular open-source projects for running and building with Nemotron 3 Ultra — star counts pulled from GitHub (July 2026).

ollama/ollama★ 175.3K
Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Go
langgenius/dify★ 147.5K
Production-ready platform for agentic workflow development.
TypeScript
open-webui/open-webui★ 144.0K
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Python
langchain-ai/langchain★ 140.8K
The agent engineering platform.
Python
ggml-org/llama.cpp★ 119.1K
LLM inference in C/C++
C++
vllm-project/vllm★ 85.2K
A high-throughput and memory-efficient inference and serving engine for LLMs
Python

Listed by GitHub stars; inclusion is by ecosystem relevance (inference engines, agent frameworks and SDKs), not affiliation. Stars change — see each repo for current numbers.

Migrating to Nemotron 3 Ultra

Coming from OpenAI or another gateway? On an OpenAI-compatible setup the only changes are base_url → https://api.datallmlab.com/v1 and model → nvidia/nemotron-3-ultra-550b-a55b. Messages, streaming, tool calls and the rest of your code stay the same. Routing & failover guide.

Self-host or use the API?

Nemotron 3 Ultra ships open weights (nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16), so you can run it yourself. Most teams still use the API: no GPU to provision or keep warm, no inference ops, and instant access across multiple providers with automatic failover. Self-host when data residency or fixed per-token economics matter most.

Rate limits & reliability

Rate limits here are the DataLLM Lab gateway's, not the upstream vendor's. On 429 (rate limited) or 503 (provider busy), retry with exponential backoff. See the error-code guide and failover setup.

Related reading

How OpenAI-Compatible APIs Work
DataLLM Lab Blog
We Benchmarked LLM Coding Cost & Quality
DataLLM Lab Blog
Best LLM API in 2026: A Buyer’s Guide
DataLLM Lab Blog

Call Nemotron 3 Ultra with one key

300+ models behind one OpenAI-compatible endpoint — better prices, better uptime, no subscriptions.

Get an API keyCompare pricing

Frequently asked questions

What is Nemotron 3 Ultra?

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). It accepts text input with a 1M-token context window and was released on 2026-06-04. On DataLLM Lab it is callable through one OpenAI-compatible endpoint.

How much does Nemotron 3 Ultra cost?

On DataLLM Lab it is $0.50 per 1M input tokens and $2.20 per 1M output tokens, with cached input at $0.10/1M — cheaper than about 40% of the 309-model catalog on output price. Pay-as-you-go, no subscription.

What is the context window of Nemotron 3 Ultra?

1M tokens, with up to 16K max output tokens.

Is Nemotron 3 Ultra open source?

Yes — open weights are published on Hugging Face (nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16). You can self-host it or call it via DataLLM Lab.

How do I call the Nemotron 3 Ultra API?

Point any OpenAI SDK at https://api.datallmlab.com/v1 and set model to "nvidia/nemotron-3-ultra-550b-a55b". One DataLLM Lab key routes this model and 300+ others; no code changes beyond the base URL and model string.

How did Nemotron 3 Ultra score in real testing?

In our executed 9-task coding benchmark it scored 8/9, averaging 48.2s per task at ~$0.00 per 1,000 tasks (real billed cost), generating 9,136 reasoning tokens. See our methodology for scope and limits.