Unlock exclusive introductory pricing for the newly launched Gemini 3.5 Flash.
Q

qwen3 max

ฤแบงu vร o:$0.8/M
ฤแบงu ra:$3.2/M
Ngร y phรกt hร nh:Jan 27, 2026

- qwen3-max: Alibaba Tongyi Qianwen team's latest Qwen3-Max model, positioned as the series' performance peak. - ๐Ÿง  Powerful Multimodal and Inference: Supports ultra-long context (up to 128k tokens) and Multimodal input, excels at complex Inference, code generation, translation, and creative content. - โšก๏ธ Breakthrough Improvement: Significantly optimized across multiple technical indicators, faster response speed, knowledge cutoff up to 2025, suitable for enterprise-level high-precision AI applications.

Sแปญ dแปฅng thฦฐฦกng mแบกi

Playground cho qwen3 max

Khรกm phรก Playground cแปงa qwen3 max โ€” mรดi trฦฐแปng tฦฐฦกng tรกc ฤ‘แปƒ kiแปƒm tra mรด hรฌnh vร  chแบกy truy vแบฅn theo thแปi gian thแปฑc. Thแปญ prompts, ฤ‘iแปu chแป‰nh tham sแป‘ vร  lแบทp lแบกi ngay lแบญp tแปฉc ฤ‘แปƒ tฤƒng tแป‘c phรกt triแปƒn vร  xรกc thแปฑc cรกc trฦฐแปng hแปฃp sแปญ dแปฅng.

technical specifications of Qwen 3-max

FieldValue / notes
Official model name / versionqwen3-max-2026-01-23 (Qwen3-Max; โ€œThinkingโ€ variant available).
Parameter scale> 1 trillion parameters (trillion-parameter flagship).
ArchitectureQwen3 family design; mixture-of-experts (MoE) techniques used across the Qwen3 lineup for efficiency; specialized โ€œthinkingโ€ / reasoning mode described.
Training data volumeReported ~36 trillion tokens (pretraining mixture reported in Qwen3 technical materials).
Native context length32,768 tokens native; validated methods (e.g., RoPE/YaRN) reported to extend behavior to much longer windows in experiments.
Typical supported modalitiesText and multimodal extensions in the Qwen3 family (image editing/vision variants exist); Qwen3-Max focuses on text + agent/tool integration for inference.
ModesThinking (step-by-step reasoning / tool use) and Non-thinking (fast instruct). Snapshot explicitly supports built-in tools.

What is Qwen3-Max

Qwen3-Max is the high-capability tier in the Qwen3 generation: an inference-focused model engineered for complex reasoning, tool/agent workflows, retrieval-augmented generation (RAG), and long-context tasks. The โ€œThinkingโ€ design enables step-by-step chain-of-thought (CoT) style outputs when required, while non-thinking modes provide lower-latency responses. The 2026-01-23 snapshot emphasized built-in tool calling and enterprise inference readiness.

Main features of Qwen3-Max

  • Frontier reasoning (โ€œThinkingโ€ mode): A reasoning/โ€œthinkingโ€ inference mode designed to produce stepwise traces and improved multi-step reasoning accuracy.
  • Trillion-parameter scale: Flagship scale intended to lift performance across reasoning, code, and alignment-sensitive tasks.
  • Long context (32K native): Native 32,768 token window; validated techniques reported to handle longer contexts in specific settings. Good for long documents, multi-document summarization, and large agent state.
  • Agent/tool integration: Designed to more effectively call external tools, decide when to search or execute code, and orchestrate multi-step agent flows for enterprise tasks.
  • Multilingual and coding strength: Trained on a massive multilingual corpus with strong performance in programming and code generation tasks.

Benchmark performance of Qwen3-Max

qwen3 max

Qwen3-Max Compare to selected contemporaries

  • Versus GPT-5.2 (OpenAI) โ€” Press comparisons position Qwen3-Max-Thinking as competitive on multi-step reasoning benchmarks when tool use is enabled; absolute ranking varies by benchmark and protocol. Qwenโ€™s price/token tiers appear positioned to be competitive for heavy agent/RAG use.
  • Versus Gemini 3 Pro (Google) โ€” Some public comparisons (HLE) show Qwen3-Max-Thinking outperforming Gemini 3 Pro on specific reasoning evaluations; again, results depend heavily on tool enabling and methodology.
  • Versus Anthropic (Claude) and other providers โ€” Qwen3-Max-Thinking is reported to match or exceed some Anthropic/Claude variants on subsets of reasoning and multi-domain benchmarks in press coverage; independent benchmark suites show mixed outcomes across datasets.

Takeaway: Qwen3-Max-Thinking is presented publicly as a frontier reasoning model that narrows or closes the gap with leading Western closed-source models on several benchmarks โ€” particularly in tool-enabled, long-context, and agentic settings. Validate with your own benchmarks and with the exact snapshot and inference configuration before committing to one model for production.

Typical / recommended use cases

  • Enterprise agents and tool-enabled workflows (automation with web search, DB calls, calculators) โ€” snapshot explicitly supports built-in tools.
  • Long-document summarization, legal/medical document analysis โ€” large context windows make Qwen3-Max suitable for long-form RAG tasks.
  • Complex reasoning and multi-step problem solving (math, code reasoning, research assistants) โ€” the Thinking mode targets chain-of-thought style workflows.
  • Multilingual production โ€” broad language coverage supports global deployments and non-English pipelines.
  • High-throughput inference with cost optimization โ€” choose model family (MoE vs dense) and snapshot appropriate to latency/cost needs.

How to access Qwen3-max API via CometAPI

Step 1: Sign Up for API Key

Log in to cometapi.com. If you are not our user yet, please register first. Sign into your CometAPI console. Get the access credential API key of the interface. Click โ€œAdd Tokenโ€ at the API token in the personal center, get the token key: sk-xxxxx and submit.

cometapi-key

Step 2: Send Requests to Qwen3-max API

Select the โ€œqwen3-max-2026-01-23โ€ endpoint to send the API request and set the request body. The request method and request body are obtained from our website API doc. Our website also provides Apifox test for your convenience. Replace with your actual CometAPI key from your account. base url is Chat Completions.

Insert your question or request into the content fieldโ€”this is what the model will respond to . Process the API response to get the generated answer.

Step 3: Retrieve and Verify Results

Process the API response to get the generated answer. After processing, the API responds with the task status and output data.

Giรก cแบฃ cho qwen3 max

Khรกm phรก mแปฉc giรก cแบกnh tranh cho qwen3 max, ฤ‘ฦฐแปฃc thiแบฟt kแบฟ ฤ‘แปƒ phรน hแปฃp vแป›i nhiแปu ngรขn sรกch vร  nhu cแบงu sแปญ dแปฅng khรกc nhau. Cรกc gรณi linh hoแบกt cแปงa chรบng tรดi ฤ‘แบฃm bแบฃo bแบกn chแป‰ trแบฃ tiแปn cho nhแปฏng gรฌ bแบกn sแปญ dแปฅng, giรบp dแป… dร ng mแปŸ rแป™ng quy mรด khi yรชu cแบงu cแปงa bแบกn tฤƒng lรชn. Khรกm phรก cรกch qwen3 max cรณ thแปƒ nรขng cao cรกc dแปฑ รกn cแปงa bแบกn trong khi vแบซn kiแปƒm soรกt ฤ‘ฦฐแปฃc chi phรญ.

ModelComet Price (USD / M Tokens)Official Price (USD / M Tokens)Discount
qwen3-max-2026-01-23
ฤแบงu vร o:$0.8/M
ฤแบงu ra:$3.2/M
ฤแบงu vร o:$1/M
ฤแบงu ra:$4/M
-20%

Mรฃ mแบซu vร  API cho qwen3 max

Truy cแบญp mรฃ mแบซu toร n diแป‡n vร  tร i nguyรชn API cho qwen3 max ฤ‘แปƒ tแป‘i ฦฐu hรณa quy trรฌnh tรญch hแปฃp cแปงa bแบกn. Tร i liแป‡u chi tiแบฟt cแปงa chรบng tรดi cung cแบฅp hฦฐแป›ng dแบซn tแปซng bฦฐแป›c, giรบp bแบกn khai thรกc toร n bแป™ tiแปm nฤƒng cแปงa qwen3 max trong cรกc dแปฑ รกn cแปงa mรฌnh.

#!/bin/bash

# Get your CometAPI key from https://api.cometapi.com/console/token
# Export it as: export COMETAPI_KEY="your-key-here"

curl https://api.cometapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -d '{
    "model": "qwen3-max-2026-01-23",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'

cURL Code Example

#!/bin/bash

# Get your CometAPI key from https://api.cometapi.com/console/token
# Export it as: export COMETAPI_KEY="your-key-here"

curl https://api.cometapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -d '{
    "model": "qwen3-max-2026-01-23",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'

Python Code Example

from openai import OpenAI
import os

# Get your CometAPI key from https://api.cometapi.com/console/token, and paste it here
COMETAPI_KEY = os.environ.get("COMETAPI_KEY") or "<YOUR_COMETAPI_KEY>"
BASE_URL = "https://api.cometapi.com/v1"

client = OpenAI(base_url=BASE_URL, api_key=COMETAPI_KEY)

completion = client.chat.completions.create(
    model="qwen3-max-2026-01-23",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
)

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

JavaScript Code Example

import OpenAI from "openai";

// Get your CometAPI key from https://api.cometapi.com/console/token, and paste it here
const api_key = process.env.COMETAPI_KEY || "<YOUR_COMETAPI_KEY>";
const base_url = "https://api.cometapi.com/v1";

const openai = new OpenAI({
  apiKey: api_key,
  baseURL: base_url,
});

const completion = await openai.chat.completions.create({
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello!" }
  ],
  model: "qwen3-max-2026-01-23",
});

console.log(completion.choices[0].message.content);

Cรกc phiรชn bแบฃn cแปงa qwen3 max

Lรฝ do qwen3 max cรณ nhiแปu snapshot cรณ thแปƒ bao gแป“m cรกc yแบฟu tแป‘ tiแปm nฤƒng nhฦฐ: sแปฑ thay ฤ‘แป•i ฤ‘แบงu ra sau cรกc bแบฃn cแบญp nhแบญt cแบงn cรกc snapshot cลฉ ฤ‘แปƒ ฤ‘แบฃm bแบฃo tรญnh nhแบฅt quรกn, cung cแบฅp cho nhร  phรกt triแปƒn thแปi gian chuyแปƒn tiแบฟp ฤ‘แปƒ thรญch แปฉng vร  di chuyแปƒn, cลฉng nhฦฐ cรกc snapshot khรกc nhau tฦฐฦกng แปฉng vแป›i cรกc endpoint toร n cแบงu hoแบทc khu vแปฑc nhแบฑm tแป‘i ฦฐu hรณa trแบฃi nghiแป‡m ngฦฐแปi dรนng. ฤแปƒ biแบฟt chi tiแบฟt vแป sแปฑ khรกc biแป‡t giแปฏa cรกc phiรชn bแบฃn, vui lรฒng tham khแบฃo tร i liแป‡u chรญnh thแปฉc.

Model idDescriptionAvailabilityRequest
qwen3-max-2026-01-23Compared to the snapshot dated September 23, 2025, this version of the Tongyi Qianwen 3 series Max model effectively integrates thinking and non-thinking modes, resulting in a comprehensive and significant improvement in overall model performance. In thinking mode, it simultaneously releases web search, web information extraction, and code interpreter tools, enabling the model to solve more challenging problems with greater accuracy by introducing external tools while thinking more slowly. This version is based on the snapshot dated January 23, 2026.โœ…Chatย format
qwen3-maxCompared to the preview version, the Tongyi Qianwen 3 series Max model has undergone specific upgrades in agent programming and tool invocation. The officially released model reaches the domain's state-of-the-art (SOTA) level, adapting to more complex agent requirements.โœ…Chatย format
qwen3-max-previewThe Tongyi Qianwen 3 series Max model Preview version effectively integrates thinking and non-thinking modes. In thinking mode, it significantly enhances capabilities in agent programming, common-sense reasoning, and mathematical/scientific/general reasoning.โœ…Chatย format