Qwen4 Max
Compare
Qwen logo

Qwen4 Max

qwen4-maxllms.txt
Qwen
New
Qwen4-Max is Tongyi Qianwen's next-generation flagship multimodal model, integrating text generation, image and video understanding, and deep reasoning capabilities. It is suitable for programming development, office work, frontend design, and complex agent tasks. The model supports internet search, tool invocation, and structured outputs, is compatible with OpenAI and Anthropic APIs, and helps developers build intelligent applications with multimodal understanding and task-execution capabilities.

Pricing

PricingCache ReadWeb SearchCache WriteCache Write 5 MinutesCache Write 1 Hour
$1.47$4.41
$0.0735/M tokens$0.00059/request$1.8375/M tokens$1.8375/M tokens$2.94/M tokens

Modalità di input

  • Text
  • Vision
  • Video

Modalità di output

  • Text

Context length

  • 1M tokens

Max output

  • 262K tokens

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Document input
  • Structured outputs
  • Structured decision
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

Fornitori

Alibaba Cloud alicloud-qwen4-max
Pricing$1.47$4.41
Cache Read$0.0735/M tokens
Web Search$0.00059/request
Cache Write$1.8375/M tokens
Cache Write 5 Minutes$1.8375/M tokens
Cache Write 1 Hour$2.94/M tokens
PrecisionⓘNot Disclosed
Latency66.3S
Throughput34.4TPS
Uptime
0.00% uptime 2 days ago
100.00% uptime yesterday
100.00% uptime today

Performance for qwen4-max

Uptime è la percentuale di richieste riuscite nelle ultime 72 ore. AIHubMix monitora continuamente ogni provider e ritenta automaticamente con il successivo miglior provider quando uno restituisce un errore o risponde troppo lentamente; Latency è il tempo totale di andata e ritorno di una richiesta (più bassa è, meglio è); Throughput indica la velocità di scrittura del modello (token al secondo; più alto è, meglio è).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="qwen4-max",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is Qwen4 Max?

Qwen4-Max is Tongyi Qianwen's next-generation flagship multimodal model, integrating text generation, image and video understanding, and deep reasoning capabilities. It is suitable for programming development, office work, frontend design, and complex agent tasks. The model supports internet search, tool invocation, and structured outputs, is compatible with OpenAI and Anthropic APIs, and helps developers build intelligent applications with multimodal understanding and task-execution capabilities.