Why is the QSP context limit 262K instead of 1M?

The model architecture can support up to 1M tokens, while QSP currently guarantees 262K tokens in production. We publish the limit we test and enforce rather than advertising a theoretical maximum.

Does it support tools and structured output?

Yes. It supports streaming, function calling, and JSON Schema structured output. QSP serves it with reasoning off, so responses are direct and carry no separate reasoning trace or hidden reasoning tokens.

How do I call it with the OpenAI SDK?

Set base_url=https://api.quicksilverpro.io/v1, use your QSP key, and set model="nemotron-3.5-lightning". Both Chat Completions and Responses API clients use the same public model ID.

262K context
Responses API

Nemotron 3.5 Lightning on QuickSilver Pro

Name: Nemotron 3.5 Lightning on QuickSilver Pro
Brand: QuickSilver Pro
Price: 0.066 USD
Availability: InStock

nemotron-3.5-lightning

NVIDIALive availability—

Nemotron 3.5 Lightning is NVIDIA's open 30B-parameter Mixture-of-Experts model with only 3B active parameters per token. It is built for fast, tool-heavy agents, high-throughput automation, and domain customization. QuickSilver Pro provides 262K-token context at $0.066 input / $0.176 output per million tokens, with zero data retention — about 10% above the lowest stable paid market rate.

262K context
131K max output
Tools
Streaming
JSON Schema output

ByRaullen ChaiUpdated August 14, 2026

You pay · input / output per 1M

$0.066 / $0.176

10% more expensive

on both legs vs Market price

Pricing comparison ($/1M tokens)

Bar length = price relative to the highest price shown

Provider	Input	Output	vs QSP
QuickSilver Pro	$0.066	$0.176	—
Market price(public paid rate)	$0.06	$0.16	10% more expensive
OpenAI (GPT-4o-mini)	$0.15	$0.60	71% lower

NVIDIA list source: huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

At a glance

Context: 262K tokens
Input / 1M: $0.066
Output / 1M: $0.176
Thinks by default: No
Max output: 131K
Latency · live: —

Fast, inexpensive tool-using agents — 30B total parameters, 3B active per token, and 262K context.

When is Nemotron 3.5 Lightning the right call?

Curated from catalog capabilities and published prices, not a benchmark.

When to use

Use Nemotron 3.5 Lightning for high-volume coding assistants, retrieval agents, long-running tool loops, structured extraction, and workflows that repeatedly reuse a large system prompt or repository context. Its sparse 30B-A3B design keeps generation inexpensive, and cached input costs $0.033 per million tokens.

Long documents and codebases, up to 262K tokens of context
Agents that call tools, with strict JSON Schema output
Responses API clients as well as Chat Completions

When to use something else

This is a fast efficiency model, not a frontier flagship. Escalate difficult research, mathematical reasoning, or complex autonomous coding to DeepSeek V4 Pro, Qwen3.8 Max, or Grok 4.6 when your evaluations justify the higher price. The QSP endpoint is text-only and currently guarantees 262K-token context with zero data retention.

Compare alternatives in Models

Quickstart (curl)

Get an API key →

curl https://api.quicksilverpro.io/v1/chat/completions \
  -H "Authorization: Bearer $QSP_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3.5-lightning",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.quicksilverpro.io/v1",
    api_key=os.environ["QSP_KEY"],
)
response = client.chat.completions.create(
    model="nemotron-3.5-lightning",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.quicksilverpro.io/v1",
  apiKey: process.env.QSP_KEY,
});
const response = await client.chat.completions.create({
  model: "nemotron-3.5-lightning",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

curl https://api.quicksilverpro.io/v1/responses \
  -H "Authorization: Bearer $QSP_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3.5-lightning",
    "input": "Hello!"
  }'

python (OpenAI SDK)

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.quicksilverpro.io/v1",
    api_key=os.environ["QSP_KEY"],
)
response = client.chat.completions.create(
    model="nemotron-3.5-lightning",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

OpenAI-compatible. One-line migration via base_url.

Gateway behavior

Compatibility notes for this model.

prompt: Prompts up to 262K tokens.
max_tokens: Up to 131K output tokens.

/v1/chat/completions: Supported
/v1/responses: Supported
streaming: Supported
tools: Supported
image input: Not listed for this model
JSON Schema: Supported
reasoning: Not listed for this model

Where the price comes from

Catalog v77 · no separate long-context tier

Provider reference: $0.06 / $0.16huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Catalog verified: 2026-09-30
Prompt cache · not compared: $0.033 read

usage.cost = prompt_tokens × $0.066/1M + completion_tokens × $0.176/1M

/pricing.json

Base rates; cached prompt tokens bill at the cache rates above.

FAQ

Common questions

$0.066 per million input tokens, $0.176 per million output tokens, and $0.033 per million cached-input tokens — about 10% above the lowest stable paid market rate.