Alibaba
Latency—
Throughput—
Upload rate—
Context length991K tokens
Max output128K tokens
Input price$2.5per 1M tokens
Output price$7.5per 1M tokens
Cache read$0.5per 1M tokens
Cache write$3.125per 1M tokens
/alibaba/qwen3.7-max
Qwen3.7-Max is a text-native reasoning model from Alibaba, built for the agent era. It is suited for frontier coding-agent work from quick frontend prototypes to complex multi-file engineering, office and productivity automation through MCP integrations and multi-agent orchestration, sustained long-horizon autonomous execution, and consistent cross-scaffold generalization across Claude Code, OpenClaw, Qwen Code and custom tool-use frameworks. It is also reliable for hard STEM and competition-level reasoning, precise instruction following, structured output and function calling, multilingual understanding and translation, and spreadsheet- and document-heavy workflows. With a 1M context window, a deep-thinking mode with a 256K chain-of-thought budget, and demonstrated ability to keep producing real improvements over 35+ hours of unattended execution, it serves as a dependable backbone for any agent system.
curl ${API_BASE_URL}/v1/chat/completions \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.7-max",
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}'Replace <YOUR_API_KEY> with the API key generated on your token management page.
All requests must include the Authorization: Bearer <TOKEN> header.
RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply by token group.