Model overview
Qwen3.7Deep thinkingText generationQwen3.7-Max is the largest and strongest model in the Qwen3.7 series. It currently exposes text-only capabilities and is designed for the agent era, with strong performance in coding, office productivity, and long-horizon autonomous execution tasks.
This model version is functionally equivalent to the snapshot model qwen3.7-max-2026-05-20.
Company: AlibabaProvider: Alibaba Cloud
Model capabilities
Input modalityT
Output modalityT
Model experience✓
Function calling✓
Structured output×
Web search✓
Prefix completion✓
Context cache✓
Batch inference✓
Fine-tuning×
Model pricing
Input$1.79/1M tokens
Input (cache hit)$0.3582/1M tokens
Input (Batch File)$0.8955/1M tokens
Explicit cache write$2.24/1M tokens
Explicit cache hit$0.1791/1M tokens
Input (Batch Chat)$1.79/1M tokens
Output$5.37/1M tokens
Output (Batch File)$2.69/1M tokens
Output (Batch Chat)$5.37/1M tokens
Tool call pricing
code_interpreter Responses APIFree
web_extractor Responses APIFree
web_search Responses API$0.597/1K calls
Rate limits and context
Maximum input length991K
Maximum input length (thinking mode)983K
Context length1M
Maximum output length64K
Maximum output length (thinking mode)64K
Maximum reasoning length256K
RPM30000
TPM5000000
API reference
EndpointPOST /v1/chat/completions
SDKOpenAI-compatible
API code examples
from openai import OpenAI import os client = OpenAI( api_key=os.getenv("WLROUTER_API_KEY"), base_url="https://api.wlrouter.com/v1", ) messages = [{"role": "user", "content": "Who are you?"}] completion = client.chat.completions.create( model="qwen3.7-max", messages=messages, extra_body={"enable_thinking": True}, stream=True ) is_answering = False print(" " + "=" * 20 + "Reasoning process" + "=" * 20) for chunk in completion: if not chunk.choices: continue delta = chunk.choices[0].delta if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None: if not is_answering: print(delta.reasoning_content, end="", flush=True) if hasattr(delta, "content") and delta.content: if not is_answering: print(" " + "=" * 20 + "Final answer" + "=" * 20) is_answering = True print(delta.content, end="", flush=True)