Nemotron 3 Super APIOPEN WEIGHTS1M context

Pricing & specs mirror our live pricing as of July 2026 (pay-as-you-go).

What is Nemotron 3 Super?

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Nemotron 3 Super on the release timeline

Nemotron 3 Super pricing

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

On output price, Nemotron 3 Super is cheaper than 78% of the 309 models in the catalog. It is served by 4 providers; the best combined rate at our last snapshot was ≈ $0.08 / $0.40 per 1M via DeepInfra, with upstream quantizations bf16, fp4, fp8.

What Nemotron 3 Super costs per month

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 Super vs alternatives

Specs

How to call Nemotron 3 Super

Copyfrom 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-super-120b-a12b",
    messages=[{"role": "user", "content": "Hello"}],
    # supports tools=[...] and tool_choice
)
print(resp.choices[0].message.content)

Copycurl https://api.datallmlab.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nvidia/nemotron-3-super-120b-a12b","messages":[{"role":"user","content":"Hello"}]}'

Copyimport 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-super-120b-a12b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(r.choices[0].message.content);

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

Prompting tips for Nemotron 3 Super

• State the goal, not every step. Nemotron 3 Super reasons internally — give it the objective, constraints and success criteria and let it plan the approach; over-scripting each step tends to lower quality. Turn effort up for hard problems.
• Huge 1M context — but anchor the ask. You can paste whole documents or codebases; models attend most to the start and end, so put the key instruction at the top and restate it after long inputs.
• Give it real tools. Pass a tools=[...] schema instead of asking it to "pretend" — let Nemotron 3 Super emit tool calls, execute them, and feed results back for the next turn.
• Constrain JSON with a schema. Use response_format / structured outputs rather than "reply in JSON" to get valid, parseable objects every time.
• Cheap enough to batch. Great for high-volume classification, extraction and drafting — template the prompt, batch requests, and validate outputs programmatically.

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

Open-source tools for Nemotron 3 Super

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

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 Super

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-super-120b-a12b. Messages, streaming, tool calls and the rest of your code stay the same. Routing & failover guide.

Self-host or use the API?

Nemotron 3 Super ships open weights (nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8, ~295.5K downloads and 262 likes in the last 30 days), with community quantizations (bf16, fp4, fp8) for smaller GPUs, 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 4 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; because Nemotron 3 Super is served by 4 providers, requests can fail over to a healthy one automatically. See the error-code guide and failover setup.

Related reading

Frequently asked questions