Qwen3.8 2.4T A95B

by alibaba · family qwen3

Facts

Release date	2026-08-12
Retired date	—
Knowledge cutoff	—
Context (max)	1,048,576
Max output	—
Modalities	text → text
Aliases	`qwen3.8-2.4t-a95bqwen3.8-2.4t`
Open weights	yes (Qwen/Qwen3.8-2.4T-A95B)
Description	Open-weight Max-class flagship: 2.4T total / 95B active MoE (512 experts, hybrid Gated DeltaNet/Attention), 262K native context extensible past 1M, 131K output. Thinking is mandatory (enable_thinking=false errors); reasoning_effort xhigh (default)/medium/low, preserve_thinking on. $2.00/$6.00 per Mtok.

Unknown values are shown as —.

Offerings

Provider	Wire ID	Variant	Endpoint	Protocol	Status	Price (USD / Mtok)	Reasoning
OpenRouter	`qwen/qwen3.8-2.4t-a95b`		chat-completions	openai-chat	ga	2.00 / 6.00	effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content

Reasoning controls

OpenRouter· qwen/qwen3.8-2.4t-a95b· chat-completions effort

reasoning.effort lowmediumhighxhigh●

effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content

Example requests

OpenRouter · openai-chat · qwen/qwen3.8-2.4t-a95b

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "qwen/qwen3.8-2.4t-a95b",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "xhigh"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "qwen/qwen3.8-2.4t-a95b",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "xhigh"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "qwen/qwen3.8-2.4t-a95b",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "xhigh"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).