All models
Qwen

Qwen3.8 Max

qwen/qwen3.8-max

Qwen3.8 Max — flagship Alibaba Qwen3.8, served on the stable paid OpenCode Go pool. Context 1M.

Pricing

Input$2.00per 1M tokens
Output$6.00per 1M tokens
Cached input$0.25per 1M tokens read from cache

Specifications

Context window1Mtokens
Max output66Ktokens
ProviderQwen
CapabilitiesVision · Reasoning · Function calling
Input typestext, image, video

Use Qwen3.8 Max

Point your existing OpenAI SDK at xKiro and pass qwen/qwen3.8-max as the model. Nothing else in your code changes.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.xkiro.com/v1",
    api_key="YOUR_XKIRO_KEY",
)

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

Supported parameters

max_tokens · temperature · top_p · stop · frequency_penalty · presence_penalty · seed · stream · tools · tool_choice · response_format · structured_outputs · reasoning · include_reasoning

Related models

Call Qwen3.8 Max through the same endpoints you already use.

Get an API key