Create an API key

Nemotron 3 Super API: toman pricing and code

nvidia/nemotron-3-super-120b-a12b

Tool callingReasoningJSON output
Create a keyTry it
Input · per 1M tokens
103,866 toman
Output · per 1M tokens
830,926 toman
One 1,000-word request ≈
1,215 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 51,933 toman per 1M tokens.Pricing and top-ups

Nemotron 3 Super example: JSON output against a schema

The example is picked from this model's own capabilities. Drop in your key and it runs as is.

from openai import OpenAI
import json

client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")

schema = {
    "name": "ticket",
    "schema": {
        "type": "object",
        "properties": {
            "category": {"type": "string", "enum": ["fani", "mali", "forush"]},
            "priority": {"type": "integer", "minimum": 1, "maximum": 5},
            "summary": {"type": "string"},
        },
        "required": ["category", "priority", "summary"],
        "additionalProperties": False,
    },
    "strict": True,
}

resp = client.chat.completions.create(
    model="nvidia/nemotron-3-super-120b-a12b",
    messages=[{"role": "user", "content": "Ticket: "For two days I cannot download my invoice and I was charged twice.""}],
    response_format={"type": "json_schema", "json_schema": schema},
)
print(json.loads(resp.choices[0].message.content))
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });

const resp = await client.chat.completions.create({
  model: "nvidia/nemotron-3-super-120b-a12b",
  messages: [{ role: "user", content: "Ticket: "For two days I cannot download my invoice and I was charged twice."" }],
  response_format: {
    type: "json_schema",
    json_schema: {
      name: "ticket",
      strict: true,
      schema: {
        type: "object",
        properties: {
          category: { type: "string", enum: ["fani", "mali", "forush"] },
          priority: { type: "integer", minimum: 1, maximum: 5 },
          summary: { type: "string" },
        },
        required: ["category", "priority", "summary"],
        additionalProperties: false,
      },
    },
  },
});
console.log(JSON.parse(resp.choices[0].message.content));
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-super-120b-a12b",
    "messages": [{"role": "user", "content": "Classify the ticket and give it a priority from 1 to 5."}],
    "response_format": {"type": "json_object"}
  }'

What is Nemotron 3 Super good for?

Nemotron 3 Super comes from NVIDIA; in uttapen you reach it with the model id "nvidia/nemotron-3-super-120b-a12b". It accepts up to 1,048,576 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 262,144 tokens. On price it sits in the "mid-range" band — cheaper than 175 and dearer than 221 of the other paid models in the catalogue.

What it can do beyond plain text: it supports tool calling, so it can invoke your own functions with valid arguments; it returns schema-valid JSON through response_format, ready to hand to your code; it has a reasoning mode that pays off on multi-step problems, maths and debugging. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.

Pricing is 103,866 toman per 1M input tokens and 830,926 per 1M output tokens. A 1,000-word round trip on Nemotron 3 Super lands near 1,215 toman. It supports cached input: repeated context is billed at 51,933 toman per 1M, which matters a lot if your system prompt is long. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.

The closest alternative with the same capabilities from a different provider is GPT Audio Mini: Nemotron 3 Super works out about 9% cheaper, and its context window is larger. Both run on the same key and the same code, so trying the other one is a single string change.

To make the figure concrete: 100,000 toman of credit buys roughly 82 thousand-word requests on Nemotron 3 Super, and every 1,000 toman is about 823 words of round trip. A job with one million input tokens and one million output tokens comes to 934,792 toman in total. Filling this model's 1,048,576-token window costs 108,911 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "nvidia/nemotron-3-ultra-550b-a55b", and choosing between those two is where most people hesitate. Both land at nearly the same price on a thousand-word request (1,215 and 1,350 toman). The context windows differ too: 1,048,576 against 262,144 tokens. Maximum answer length differs as well: 262,144 against 182,520 tokens. On parameters, this one takes logprobs, top_logprobs.

NVIDIA has 12 models in our catalogue; the cheapest is Nemotron 3.5 Lightning at 122 toman per thousand words and the dearest Nemotron 3 Ultra at 1,350. Among the less common parameters it accepts logit_bias, logprobs, min_p, presence_penalty, reasoning_effort, repetition_penalty — all through the standard request body. By context size the nearest option from another provider is DeepSeek V4 Flash 0423 at 1,048,576 tokens.

Good fits: product chatbots and internal assistants, where cost and quality have to balance, logic puzzles and code review, agents that reach out to APIs and databases, extracting data against a fixed schema, analysing a long document or codebase in one request.

Provider's own description

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...

Three real jobs, priced on this model

Each figure is derived from the prices above and moves when they do.

JobTokensCost
One chat turn with a medium history1,500 in + 400 out488 toman
Summarising a ten-page document4,000 in + 600 out914 toman
Classifying a thousand short rows120,000 in + 20,000 out29,082 toman

Price history

DateInput (toman/1M)Output (toman/1M)
28 Oct 2026103,866830,926
28 Oct 202627,698155,799
21 Oct 2026103,866830,926
21 Oct 202627,698155,799
21 Oct 2026103,866830,926
8 Oct 202627,698155,799
8 Oct 202629,429138,488
14 Sep 202627,698155,799
7 Sep 202629,429138,488

Every price change for this model is recorded. Toman figures use today's rate.

Frequently asked

How do I call Nemotron 3 Super from Iran?
Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "nvidia/nemotron-3-super-120b-a12b". Nothing else in your code changes.
What does Nemotron 3 Super cost in toman?
103,866 toman per 1M input tokens and 830,926 toman per 1M output tokens; a 1,000-word request is around 1,215 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Nemotron 3 Super take?
Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 262,144 tokens.
Does Nemotron 3 Super support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Structured output through response_format works too.