Skip to content
  • 1M context
  • Responses API

Qwen3.6 Plus on QuickSilver Pro

qwen3.6-plus
Alibaba / QwenLive availability—

Qwen 3.6 Plus is Alibaba's 1-trillion-parameter MoE flagship — sized between 3.6-35B and 3.7 Max, with 1M context. On QuickSilver Pro it's $0.26 input / $1.56 output per 1M tokens, ~20% below OpenRouter and ~10× lower than GPT-4o on output. The sweet spot for teams who need 3.5/3.6-35B's price economics but with more reasoning depth and a million-token context.

  • 1M context
  • Tools
  • Streaming
  • JSON Schema output

You pay · input / output per 1M

$0.26 / $1.56

20% lower

on both legs vs OpenRouter

Pricing comparison ($/1M tokens)

Bar length = price relative to the highest price shown

ProviderInputOutputvs QSP
QuickSilver Pro$0.26$1.56lowest-cost
OpenRouter(qwen/qwen3.6-plus)$0.325$1.9520% lower
OpenAI (GPT-4o)$2.50$10.0084% lower

OpenRouter list source: openrouter.ai/qwen/qwen3.6-plus

At a glance

Context
1M tokens
Input / 1M
$0.26
Output / 1M
$1.56
Thinks by default
No
Latency · live
—

Production reasoning + long-context RAG at 10× lower output than GPT-4o.

When is Qwen3.6 Plus the right call?

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

When to use

3.6 Plus sits in the production-default slot: too small a step from 3.6-35B to skip, too low-cost to ignore for reasoning-heavy workloads. Use it for multi-document RAG over 100K+ tokens, customer-facing chat where you want noticeable answer-quality bumps over 3.6-35B without 3.7 Max's price, agentic workflows where the per-call latency penalty of thinking is acceptable, and Chinese-language tasks where Qwen's training data advantage compounds.

  • Long documents and codebases, up to 1M 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

For deterministic, no-thinking production chat where token budgets must be tight, DeepSeek V4 Flash ($0.06/$0.18) with reasoning.enabled=false is the lower non-thinking choice. For frontier-level reasoning that 3.6 Plus visibly fails at on your eval, step up to 3.7 Max or V4 Pro. QuickSilver Pro serves 3.6 Plus in non-thinking mode: replies are direct, and a reasoning field in the request does not turn thinking on.

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": "qwen3.6-plus",
    "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="qwen3.6-plus",
    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: "qwen3.6-plus",
  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": "qwen3.6-plus",
    "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="qwen3.6-plus",
    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 1M 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 v72 · no separate long-context tier

Provider reference
$0.325 / $1.95openrouter.ai/qwen/qwen3.6-plus
Catalog verified
Prompt cache · not compared
$0.325 5m write

usage.cost = prompt_tokens × $0.26/1M + completion_tokens × $1.56/1M

/pricing.json

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

FAQ

Common questions

3.6-35B is the compact MoE tier (35B params, 3B active, 262K context, $0.05/$0.70 per 1M tokens). 3.6 Plus is the next step up — 1T-parameter MoE, 1M context, $0.26/$1.56 per 1M tokens. The price gap is meaningful, but the answer-quality bump and wider context justify it where 3.6-35B hits its ceiling.

Qwen3.6 Plus

Try Qwen3.6 Plus with double credits — up to $50 in bonus credits

Get API Key

$0.26 / $1.56in / out per 1M tokens

TryGet API Key