Qwen3 Max
Qwen3 Max is the flagship of Alibaba's Qwen3 family, a trillion-parameter-class model built for top-tier reasoning, coding, and multilingual performance. It supports very long context, strong Arabic and Chinese coverage, and competitive agentic tool use. Use it as a frontier-tier alternative when open-ecosystem familiarity and broad-language quality matter.
Pricing
Input
$0.845 / 1M
Output
$3.38 / 1M
Pay only for what you use. No subscriptions, no minimums.
Specs
- Context
- 256K
- Max output
- 64K
- Latency
- Medium
- Category
- Text
- Arabic
- Strong
Quick start
Use any OpenAI-compatible client. Just change base_url and your key.
from openai import OpenAI
client = OpenAI(
api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
base_url="https://api.thalam.ai/v1",
)
response = client.chat.completions.create(
model="qwen/qwen3-max",
messages=[
{"role": "user", "content": "Hello from Thalam!"}
],
)
print(response.choices[0].message.content)Similar models
GPT-5.6 Sol
The top tier of OpenAI's GPT-5.6 generation. Frontier reasoning, coding, and agentic work with a 1M-token context and image input.
GPT-5.6 Terra
The balanced tier of OpenAI's GPT-5.6 generation. Same 1M-token context and image input, tuned for everyday production work.