- 262K context
- Multimodal
- Reasoning
- Responses API
- NEW · Nov 10
Qwen4-Max Preview on QuickSilver Pro
Qwen4-Max Preview is a preview for complex coding, knowledge work, front-end builds and professional software workflows. $2.00 input / $6.00 output per million tokens. Available through Chat Completions and Responses.
- 262K context
- 66K max output
- Vision
- Tools
- Reasoning · off by default
- Streaming
- JSON Schema output
You pay · input / output per 1M
$2.00 / $6.00
Alibaba list source: qwen.ai
At a glance
- Context
- 262K tokens
- Input / 1M
- $2.00
- Output / 1M
- $6.00
- Thinks by default
- No
- Max output
- 66K
- Latency · live
- —
Complex coding, knowledge work and agent workflows (preview).
When is Qwen4-Max Preview the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
Use Qwen4-Max Preview for coding and agent evaluations. Supported capabilities: text input, text output, image input, streaming, reasoning, tool calling and JSON Schema. Thinking is off by default; set enable_thinking=true to enable it, or false to disable it.
- Long documents and codebases, up to 262K tokens of context
- Agents that call tools, with strict JSON Schema output
- Prompts that include images
- Direct replies, with reasoning off by default
When to use something else
Preview behavior can change. QuickSilver Pro currently uses conservative limits of 262K context tokens and 66K maximum output tokens because verified metadata does not expose the model’s full limits. Evaluate critical workflows before adopting it.
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-preview",
"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-preview",
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-preview",
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-preview",
"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-preview",
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 66K 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.qwen.ai
- Catalog verified
- Prompt cache · not compared
- $0.25 read · $2.50 5m write
usage.cost = prompt_tokens × $2.00/1M + completion_tokens × $6.00/1M
FAQ
Common questions
$2.00 input / $6.00 output per million tokens, matching Qwen3.8 Max on QuickSilver Pro. Cache reads cost $0.25 and cache writes $2.50 per million tokens.
262K context tokens and up to 66K output tokens. These are conservative QSP limits, not a claim about the model’s maximum context. Input and output must fit together.
Set model="qwen4-max-preview" and base_url="https://api.quicksilverpro.io/v1" in the OpenAI SDK. Supported APIs: Chat Completions and Responses. This preview has limited capacity; retry after a model_at_capacity error.