Refract › Models › Qwen 3.8 Max

Qwen 3.8 Max API

Use Qwen 3.8 Max by Qwen through Refract's OpenAI-compatible API for $0.24 per 1M input and $0.72 per 1M output tokens, 88% below the official $2 / $6. Pay per token, no subscription.

Chat with Qwen 3.8 Max · Get an API key

Use it from code

curl https://refracthub.com/v1/chat/completions \
  -H "Authorization: Bearer $REFRACT_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen3.8-max", "messages": [{"role": "user", "content": "Hello"}]}'

from openai import OpenAI

client = OpenAI(base_url="https://refracthub.com/v1", api_key="YOUR_REFRACT_KEY")
reply = client.chat.completions.create(model="qwen3.8-max", messages=[{"role": "user", "content": "Hello"}])
print(reply.choices[0].message.content)

Questions

How much does Qwen 3.8 Max cost on Refract?

$0.24 per 1M input tokens and $0.72 per 1M output tokens, compared with $2 and $6 on Qwen's official API. You pay only for the tokens you use, with no subscription.

Does it work with the OpenAI SDK?

Yes. Point the OpenAI SDK, or any OpenAI-compatible app, at https://refracthub.com/v1 with your Refract key and use the model name "qwen3.8-max". The Anthropic Messages format works too.

Can I use Qwen 3.8 Max without writing code?

Yes. Chat with it on the web at https://refracthub.com/chat, or use the Refract desktop app for Windows.

All 39 models