Home › VastLLM Catalog › Qwen3.7 Max
Qwen3.7 Max
by Alibaba(Qwen) · Language Models
Context 1M tokensReasoning / thinking
by Alibaba(Qwen) · Language Models
Qwen3.7-Max is Alibaba's proprietary flagship large language model, launched May 2026 and built for long-horizon agentic work, coding and complex reasoning. It pairs a 1M-token context window with a native extended-thinking mode and supports very long autonomous tool-use runs, including external harnesses like Claude Code. It ranked as the highest-placed Chinese model on the Artificial Analysis Intelligence Index v4.0 at launch and is served via Alibaba Cloud Model Studio with no open weights. Ideal for autonomous coding agents, multi-step office automation and demanding reasoning workloads where cost matters relative to Western frontier models.
$1.2741 in · $3.8232 out · $0.2548 cached / 1M
| Usage | Rate (USD) | Unit |
|---|---|---|
| Input tokens | $1.2741 | per 1M tokens |
| Cached input (cache hit) | $0.2548 | per 1M tokens |
| Output tokens | $3.8232 | per 1M tokens |
Official model pricing · currency: USD · pre-deduction settled by actual usage
OpenAI-compatible · base URL https://api.tunerouter.com/v1/
curl https://api.tunerouter.com/v1/chat/completions \
-H "Authorization: Bearer $TUNEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "qwen3.7-max", "messages": [{"role": "user", "content": "Hello!"}]}'Model ID: qwen3.7-max · works with OpenAI SDKs — just point base_url at api.tunerouter.com