- 1M context
- Multimodal
- Reasoning
- Responses API
Qwen4-Max on QuickSilver Pro
Qwen4-Max. Qwen4 flagship for coding and agent workflows. $1.50 input / $4.50 output per million tokens.
- 1M context
- 131K max output
- Vision
- Tools
- Reasoning · on by default
- Streaming
- JSON Schema output
You pay · input / output per 1M
$1.50 / $4.50
Alibaba list source: alibabacloud.com/help/en/model-studio/qwen4-max
At a glance
- Context
- 1M tokens
- Input / 1M
- $1.50
- Output / 1M
- $4.50
- Thinks by default
- Yes
- Max output
- 131K
- Latency · live
- —
Qwen4 flagship for coding and agent workflows.
When is Qwen4-Max the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
Thinking is on by default (high). Set reasoning_effort=low or enable_thinking=false. For tool calls and strict JSON Schema, set enable_thinking=false. Supports automatic, required and named tool calls, image input and streaming. text input, text output, image input, streaming, reasoning, tool calling and JSON Schema
- Long documents and codebases, up to 1M tokens of context
- Agents that call tools, with strict JSON Schema output
- Prompts that include images
- Multi-step reasoning, on by default
When to use something else
QSP caps output at 131,072 tokens in both modes. Thinking and answer share the budget; reasoning tokens are billed once as output. Video input is not verified.
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": "qwen4-max",
"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="qwen4-max",
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: "qwen4-max",
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": "qwen4-max",
"input": "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="qwen4-max",
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.
max_tokens- Up to 131K output tokens.
- /v1/chat/completions: Supported
- /v1/responses: Supported
- streaming: Supported
- tools: Supported
- image input: Supported
- JSON Schema: Supported
- reasoning: Supported
Where the price comes from
- Provider reference
- No provider list price is compared for this model.alibabacloud.com/help/en/model-studio/qwen4-max
- Catalog verified
- Prompt cache · not compared
- $0.075 read
usage.cost = prompt_tokens × $1.50/1M + completion_tokens × $4.50/1M
FAQ
Common questions
Qwen4-Max. Qwen4 flagship for coding and agent workflows. $1.50 input / $4.50 output per million tokens. Cache reads $0.075/M. Prices are flat through the full 1M context.
1M context tokens and up to 131K output tokens. Input and output must fit together. QSP caps output at 131,072 tokens in both modes. Thinking and answer share the budget; reasoning tokens are billed once as output. Video input is not verified.
base_url=https://api.quicksilverpro.io/v1; model="qwen4-max". Chat Completions and Responses.