Qwen3.6 Max Preview | Qwen LLM API Pricing & Performance

Name: Qwen3.6 Max Preview API
Brand: qwen
Price: 1.3 USD
Availability: InStock

Utilisation de l'API

Utilisez les exemples de code suivants pour intégrer notre API :

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="qwen/qwen3.6-max-preview",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

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

Introduction au modèle

Qwen: Qwen3.6 Max Preview

Why It Looks Great

Proprietary frontier Qwen model for demanding reasoning and coding workloads
Sparse Mixture-of-Experts architecture with approximately 1T total parameters
Strong fit for agentic coding, tool use, complex reasoning, and instruction-following tasks
262K-token context window for long prompts, repository-scale context, documents, and multi-turn workflows
Up to 64K output tokens for extended reasoning, coding, and structured generation
Thinking mode support for reasoning-heavy requests
Function calling and tool-use support for agentic application workflows
Structured output support for JSON responses and schema-constrained generation

Key Features

Architecture: Sparse Mixture-of-Experts
Total Parameters: approximately 1T
Context Window: 262,144 tokens
Max Input: 196,608 tokens
Max Output: 65,536 tokens
Thinking Budget: 128K tokens
Input: Text
Output: Text
Vision: Not listed
Function Calling: Supported
Structured Outputs: Supported
Thinking Mode: Supported
Built-in Tools: Not listed
Batch Calling: Not listed
Audio Input: Not listed
Image Generation: Not listed
Supported Parameters: include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p

Specifications

Specification	Value
Provider	alibaba
Model Type	Chat Completions model
Architecture	Sparse Mixture-of-Experts
Parameters	approximately 1T
Modalities	text->text
Context Window	262,144 tokens
Max Input	196,608 tokens
Max Output	65,536 tokens
Thinking Budget	128K tokens
Input	Text
Output	Text
Vision	Not listed
Function Calling	Supported
Structured Outputs	Supported
Thinking Mode	Supported
Release	April 2026

Pricing

Token Type	Cost
Input	$1.04 per million tokens
Output	$6.24 per million tokens
Cache Write	$1.30 per million tokens

How to Use

Write your prompt - describe the task, provide context, and specify the desired output format.
Submit - the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1
API Endpoint: chat/completions
Model ID: qwen/qwen3.6-max-preview

API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="qwen/qwen3.6-max-preview",
    messages=[{"role": "user", "content": "Hello!"}]
)

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

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen/qwen3.6-max-preview",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

Model: qwen/qwen3.6-max-preview
Provider: alibaba
Best suited for high-end reasoning, agentic coding, tool use, long-context text workflows, and structured output generation

Qwen3.6 Max Preview API

qwen/qwen3.6-max-preview

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse Mixture-of-Experts architecture with approximately 1T total parameters. It is optimized for high-end reasoning, agentic coding, tool use, instruction following, and complex text generation workflows. The model supports a 262K-token context window, up to 64K output tokens, thinking mode, function calling, and structured outputs, making it suitable for demanding production tasks that require stronger reasoning capability over raw throughput.

Questions fréquentes sur Qwen3.6 Max Preview

Combien coûte l'API Qwen3.6 Max Preview ?+

Tarification sur WaveSpeedAI : $1.30 par million de tokens d'entrée et $7.80 par million de tokens de sortie. Le prompt caching et le traitement par batch sont facturés séparément et réduisent le coût effectif sur les charges longues et répétitives.

Quelle est la fenêtre de contexte de Qwen3.6 Max Preview ?+

Qwen3.6 Max Preview prend en charge jusqu'à 262K tokens de contexte et jusqu'à 66K tokens de sortie par requête.

Qwen3.6 Max Preview est-il compatible avec OpenAI ?+

Oui. WaveSpeedAI expose Qwen3.6 Max Preview via un endpoint compatible OpenAI à https://llm.wavespeed.ai/v1. Pointez le SDK officiel d'OpenAI vers cette base URL avec votre clé API WaveSpeedAI — aucune autre modification de code requise.

Comment démarrer avec Qwen3.6 Max Preview ?+

Connectez-vous à WaveSpeedAI, créez une clé API dans Access Keys, puis envoyez une requête à https://llm.wavespeed.ai/v1/chat/completions avec l'id du modèle affiché ci-dessus. Les nouveaux comptes reçoivent des crédits gratuits pour évaluer Qwen3.6 Max Preview.

Tarification

Essayer le modèle