uttapen

Nemotron 3.5 Lightning API: toman pricing and code

nvidia/nemotron-3.5-lightning

toolsreasoningjson
Input · per 1M tokens
23,210 toman
Output · per 1M tokens
58,025 toman
One 1,000-word request ≈
106 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 11,605 toman / 1M.Pricing and top-ups

Nemotron 3.5 Lightning example: tool calling

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-…")

tools = [{
    "type": "function",
    "function": {
        "name": "check_stock",
        "description": "Returns the stock level of a product",
        "parameters": {
            "type": "object",
            "properties": {"sku": {"type": "string"}},
            "required": ["sku"],
        },
    },
}]

messages = [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}]
first = client.chat.completions.create(model="nvidia/nemotron-3.5-lightning", messages=messages, tools=tools)
call = first.choices[0].message.tool_calls[0]

# you run the function yourself — the model never touches the database
args = json.loads(call.function.arguments)
result = {"sku": args["sku"], "qty": 7}

messages += [first.choices[0].message, {"role": "tool", "tool_call_id": call.id, "content": json.dumps(result)}]
final = client.chat.completions.create(model="nvidia/nemotron-3.5-lightning", messages=messages, tools=tools)
print(final.choices[0].message.content)

What is Nemotron 3.5 Lightning good for?

NVIDIA publishes this model; we expose it under the id "nvidia/nemotron-3.5-lightning". Its context window is 262,144 tokens, roughly 197k English words in one request. A single response can run to 131,072 tokens. On price it sits in the "very cheap" band — cheaper than 33 and dearer than 373 of the other paid models in the catalogue.

Capabilities available on this id: 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.

For a back-of-envelope figure: about 106 toman per 1,000-word exchange (23,210 in, 58,025 out, per 1M tokens). It supports cached input: repeated context is billed at 11,605 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 Qwen2.5 7B Instruct: Nemotron 3.5 Lightning works out roughly 1.1× 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 943 thousand-word requests on Nemotron 3.5 Lightning, and every 1,000 toman is about 9,434 words of round trip. A job with one million input tokens and one million output tokens comes to 81,235 toman in total. Filling this model's 262,144-token window costs 6,084 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-lightning: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: 262,144 against 1,000,000 tokens. Maximum answer length differs as well: 131,072 against 65,536 tokens. On parameters, this one takes frequency_penalty, logit_bias, logprobs, min_p.

NVIDIA has 10 models in our catalogue; the cheapest is Nemotron 3 Nano 30B A3B at 94 toman per thousand words and the dearest Nemotron 3 Ultra at 1,414. Among the less common parameters it accepts logit_bias, logprobs, min_p, repetition_penalty, top_k, top_logprobs — all through the standard request body. By context size the nearest option from another provider is Trinity Large Thinking at 262,144 tokens.

What to use it for: high-volume work such as classification, tagging and bulk summarising, 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 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

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 out58 toman
Summarising a ten-page document4,000 in + 600 out128 toman
Classifying a thousand short rows120,000 in + 20,000 out3,946 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-lightning:free01,000,000

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

Frequently asked

How do I call Nemotron 3.5 Lightning 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-lightning". Nothing else in your code changes.
What does Nemotron 3.5 Lightning cost in toman?
23,210 toman per 1M input tokens and 58,025 toman per 1M output tokens; a 1,000-word request is around 106 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Nemotron 3.5 Lightning take?
Up to 262,144 tokens per request, roughly 197k words. A single answer can reach 131,072 tokens.
Does Nemotron 3.5 Lightning 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.