Qwen

Qwen3.6 MAX Preview

Alibaba Qwen 3.6 Max Preview, a sparse mixture-of-experts model with ~1 trillion parameters. Optimized for agentic coding, tool use, and long-context reasoning with an integrated thinking mode that preserves reasoning traces across multi-turn conversations. 262K context window, available via Alibaba Cloud Model Studio API.

  • Raisonnement
  • Utilisation d’outils
  • Sortie structurée
  • Contexte long

La description n’est pas encore disponible dans cette langue ; elle est affichée en anglais.

Utiliser dans la consoleqwen3.6-max-preview

USD

Tarifs

default
input<128K
Entrée$1.33/1M tokensPrix de complétion$8/1M tokensLecture cache$0.1268/1M tokensÉcriture cache$1.585/1M tokens
input>=128K
Entrée$2.21/1M tokensPrix de complétion$13.3/1M tokensLecture cache$0.22/1M tokensÉcriture cache$2.77/1M tokens

Prix publics en dollars US. Le coût final peut varier selon le groupe de compte et le volume d’utilisation.

API

Exemples de code

curl --location --request POST 'https://api.tokenhot.cn/v1/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "qwen3.6-max-preview",
    "messages": [
        {
            "role": "user",
            "content": "What model are you"
        }
    ]
}'

Qwen

Modèles associés

QwenQwenQwen3.6 Flash

Designed for agentic workloads, coding, and office productivity, with a stronger combined focus on long context, tool calling, and structured output than Qwen3.5. Compared with flagship models such as GPT, Claude, and Gemini, it is a cost-effective alternative for Chinese, coding, and multi-step tool workflows.

$0.1785/1M tokens
QwenQwenQwen3.6 Plus

Designed for agentic workloads, coding, and office productivity, with a stronger combined focus on long context, tool calling, and structured output than Qwen3.5. Compared with flagship models such as GPT, Claude, and Gemini, it is a cost-effective alternative for Chinese, coding, and multi-step tool workflows.

$0.3/1M tokens
QwenQwenQwen3.8 MAX

Qwen's most capable flagship multimodal reasoning model, built for long-horizon coding, professional work, and multi-stage agent tasks. It accepts text, images, and video, offers a 1M-token context window with up to 128K output, and supports function calling, structured outputs, web search, and a code interpreter. It is best used as a high-quality workhorse for complex tasks rather than for the lowest-cost, lowest-latency batch workloads.

$1.775/1M tokens
QwenQwenQwen3.7 Plus

Designed for agentic workloads, coding, and office productivity, with a stronger combined focus on long context, tool calling, and structured output than Qwen3.6. Compared with flagship models such as GPT, Claude, and Gemini, it is a cost-effective alternative for Chinese, coding, and multi-step tool workflows.

$0.295/1M tokens

FAQ

Questions fréquentes

À quels usages Qwen3.6 MAX Preview convient-il ?

Qwen3.6 MAX Preview convient aux types d’entrée, de sortie et de capacités indiqués sur cette page. Testez vos charges réelles avant un usage critique.

Comment Qwen3.6 MAX Preview est-il facturé ?

Les tarifs figurent ci-dessus. Le coût réel dépend du volume, du groupe de compte et du contenu de la requête.

Comment appeler Qwen3.6 MAX Preview ?

Utilisez l’identifiant du modèle ci-dessus avec un protocole API pris en charge. Des exemples sont affichés lorsqu’ils sont disponibles.

Commencer

Créez avec Qwen3.6 MAX Preview

Utiliser dans la console