qwen3.8-2.4t-a95b

Name: qwen/qwen3.8-2.4t-a95b
Brand: Alibaba
Price: 2.5 USD
Availability: InStock

AlibabaAdded Aug 19, 2026

Model idqwen/qwen3.8-2.4t-a95b

The first open release of a Qwen Max-class model: 2.4T parameters with 95B active, text only, thinking always on. Qwen reports gains in coding and long, multi-step agent work, with better handling of environment feedback along the way.

Cost /1M tokens

$2.50input

$0.50cached

$6.25output

Context

986Ktokens

Live speed

191 tok/s · 1.38s to first token

Speed

Throughput users got on qwen3.8-2.4t-a95b with Keln API in the last 24 hours.

Latency

Time to first token users got on qwen3.8-2.4t-a95b with Keln API in the last 24 hours.

Capabilities

Input

Text

Tool calling

Yes

JSON output

Yes

Reasoning

Yes

Web search

With opt-in

Data retention

Zero

Use the API

Create an API key, save it to KELN_API_KEY, then call the endpoint below.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.keln.ai/v1/",
    api_key=os.environ.get("KELN_API_KEY"),
)

resp = client.chat.completions.create(
    model="qwen/qwen3.8-2.4t-a95b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)