---
id: "qwen/qwen3.7-max"
also: ["qwen/qwen3.7-max-20260520", "requesty/alibaba/qwen3.7-max", "vercel/alibaba/qwen3.7-max"]
cheapest_list_usd_per_m: "1.475 in, 4.425 out, at alibaba on openrouter"
cheapest_effective_usd_per_m: "0.6275 in, 4.4245 out, at alibaba on openrouter"
context: 1000000
max_output: 131072
input: ["text"]
output: ["text"]
released: "2026-05-21"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 4
gateways: "openrouter (2), requesty (1), vercel (1)"
no_training: 4
trains: 0
retains_prompts: 2
coding: 66
agentic: 22.5000
---
# Qwen: Qwen3.7 Max

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks, and long-horizon autonomous execution. The model offers notable gains in coding and agentic performance over prior Qwen generations and supports explicit prompt caching for efficient repeated context use.