Create an API key

Nemotron 3.5 Super VL API: toman pricing and code

nvidia/nemotron-3.5-super-vl

Image inputTool callingReasoningJSON output
Create a keyTry it
Input · per 1M tokens
51,933 toman
Output · per 1M tokens
173,110 toman
One 1,000-word request ≈
293 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 6,924 toman per 1M tokens.Pricing and top-ups

Nemotron 3.5 Super VL example: reading an image into JSON

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

# tip: a data URI works too — base64 the file and prefix it with data:image/jpeg;base64,
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3.5-super-vl",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Return only the invoice number and the total, as JSON."},
        {"type": "image_url", "image_url": {"url": "https://example.com/factor.jpg"}}
      ]
    }]
  }'
import base64, json
from openai import OpenAI

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

img = base64.b64encode(open("factor.jpg", "rb").read()).decode()

resp = client.chat.completions.create(
    model="nvidia/nemotron-3.5-super-vl",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Return the invoice number, the date and the total as JSON."},
            {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{img}"}},
        ],
    }],
    response_format={"type": "json_object"},
)
print(json.loads(resp.choices[0].message.content))
import OpenAI from "openai";
import { readFileSync } from "node:fs";

const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const img = readFileSync("factor.jpg").toString("base64");

const resp = await client.chat.completions.create({
  model: "nvidia/nemotron-3.5-super-vl",
  messages: [{
    role: "user",
    content: [
      { type: "text", text: "Return the invoice number, the date and the total as JSON." },
      { type: "image_url", image_url: { url: `data:image/jpeg;base64,${img}` } },
    ],
  }],
  response_format: { type: "json_object" },
});
console.log(JSON.parse(resp.choices[0].message.content));

What is Nemotron 3.5 Super VL good for?

NVIDIA publishes this model; we expose it under the id "nvidia/nemotron-3.5-super-vl". Its context window is 1,048,576 tokens, roughly 786k English words in one request. A single response can run to 943,718 tokens. On price it sits in the "very cheap" band — cheaper than 300 and dearer than 85 of the other paid models in the catalogue.

What it can do beyond plain text: it reads images directly, which makes it a real option for invoices, forms and screenshots; 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 51,933 toman per 1M input tokens and 173,110 per 1M output tokens. A 1,000-word round trip on Nemotron 3.5 Super VL lands near 293 toman. It supports cached input: repeated context is billed at 6,924 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 Claude Haiku 5.5: Nemotron 3.5 Super VL works out about 10% more expensive, 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 341 thousand-word requests on Nemotron 3.5 Super VL, and every 1,000 toman is about 3,413 words of round trip. A job with one million input tokens and one million output tokens comes to 225,043 toman in total. Filling this model's 1,048,576-token window costs 54,456 toman on the input side alone, which is the real reason to keep conversation history short.

This id gets confused with "nvidia/nemotron-3.5-super-vl:free", because the underlying model is the same. The difference is the suffix: no suffix (the standard variant) against "free". The context windows differ too: 1,048,576 against 1,000,000 tokens. Maximum answer length differs as well: 943,718 against 131,072 tokens. On parameters, this one takes frequency_penalty, logit_bias, logprobs, min_p.

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, repetition_penalty, top_k — 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: high-volume work such as classification, tagging and bulk summarising, logic puzzles and code review, pulling text and fields out of images, 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 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

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 out147 toman
Summarising a ten-page document4,000 in + 600 out312 toman
Classifying a thousand short rows120,000 in + 20,000 out9,694 toman

Other variants of this model

Same core model, different execution terms and different price. This page is the standard variant.

VariantModel idOutput / 1MContext
freenvidia/nemotron-3.5-super-vl:free01,000,000

Put the variant's id verbatim in the model field; nothing else in your code changes.

Price history

DateInput (toman/1M)Output (toman/1M)
20 Oct 202651,933173,110
18 Oct 202634,622138,488
18 Oct 202651,933173,110
17 Oct 202634,622138,488
15 Oct 202651,933173,110

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

Frequently asked

How do I call Nemotron 3.5 Super VL 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-3.5-super-vl". Nothing else in your code changes.
What does Nemotron 3.5 Super VL cost in toman?
51,933 toman per 1M input tokens and 173,110 toman per 1M output tokens; a 1,000-word request is around 293 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Nemotron 3.5 Super VL take?
Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 943,718 tokens.
Does Nemotron 3.5 Super VL support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Image input is accepted through image_url, as a data URI or a public URL. Structured output through response_format works too.