Qwen3.7 Max
Qwen
qwen/qwen3.7-max
Tongyi flagship reasoning, agentic optimized
Context Window
1.0M
1,048,576 tokens
Max Output
66K
65,536 tokens
About this model
Qwen 3.7 Max is Alibaba's newly released flagship Tongyi model on the Bailian platform, featuring a 1M token context window and state-of-the-art reasoning/CoT capability. Optimized specifically for multi-step agent workflows and deep codebase engineering, with highly cost-effective context cache billing.
Highlights
Qwen flagship
1M context
Reasoning & CoT optimized
Context cache
Best For
Long-horizon agent workflowsDeep logical & math reasoningComplex codebase engineeringBilingual multimodal tasks
2026-05-26MoE TransformerProprietary
Capabilities
ChatReasoningCodetoolscache
Pricing (per 1M tokens)
| Pricing (per 1M tokens) | / 1M tokens |
|---|---|
| Input / 1M | $2.63 |
| Output / 1M | $7.88 |
| Cache Read | $0.263 |
| Cache Write | $3.28 |
Final prices shown
Quick Start
main.py
from openai import OpenAI client = OpenAI( base_url="https://api.chuizi.ai/v1", api_key="ck-your-key-here", ) response = client.chat.completions.create( model="qwen/qwen3.7-max", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)