Qwen3.8-Max

Alibaba 2.4-trillion-parameter MoE flagship (95B active) for coding and office productivity.

Alibabaqwen3.8-max2026-08-03Report incorrect data

Specs

Context: 1M
Max output: 131.1K
Input price: $2/ 1M tokens
Output price: $6/ 1M tokens
Released: 2026-08-03

Context

Context window: 1M
Max input: 991.8K
Max output: 131.1K

Pricing · USD / 1M tokens

Input: $2
Output: $6
Cache read: $0.17
Cache write: $2.5

Modalities

Input: TextImageVideo
Output: Text

API

API types: chatmessagesresponses

Reasoning

Reasoning: Yes
Levels: —

Info

Status: Active
Released: 2026-08-03
Knowledge cutoff: —

Features

Confirmed: toolsstructured_outputstreamingcachingbatch

How to call

alibabamodel = qwen3.8-maxreasoning = enable_thinking

chat

POSThttps://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions

messages

POSThttps://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/apps/anthropic/v1/messages

responses

POSThttps://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses

JSON

qwen3.8-max.json

{
  "id": "qwen3.8-max",
  "object": "model",
  "created": 1785715200,
  "owned_by": "alibaba",
  "name": "Qwen3.8-Max",
  "api": {
    "types": [
      "chat",
      "messages",
      "responses"
    ]
  },
  "limits": {
    "context": 1000000,
    "input": 991808,
    "output": 131072
  },
  "modalities": {
    "input": [
      "text",
      "image",
      "video"
    ],
    "output": [
      "text"
    ]
  },
  "reasoning": {
    "supported": true,
    "efforts": []
  },
  "pricing": {
    "currency": "USD",
    "unit": "1M_tokens",
    "input": 2,
    "output": 6,
    "cache_read": 0.17,
    "cache_write": 2.5
  },
  "features": [
    "tools",
    "structured_output",
    "streaming",
    "caching",
    "batch"
  ],
  "info": {
    "status": "active",
    "release_date": "2026-08-03",
    "knowledge_cutoff": null,
    "description": "Alibaba 2.4-trillion-parameter MoE flagship (95B active) for coding and office productivity.",
    "docs": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-max",
    "verified_at": "2026-10-11"
  }
}

Official sources