| qwen3.6-flash | qwen3.7-plus | |
|---|---|---|
| Providers | Alibaba Qwen | Alibaba Qwen |
| Input $/M | $0.18 | $0.30 |
| Output $/M | $1.09 | $1.21 |
| Output multiplier | ×6.00 | ×4.00 |
| Context window | 1M tokens | 1M tokens |
| Intelligence index | — | — |
| Coding index | — | 55.9 |
qwen3.6-flash is roughly 1.7× cheaper on input than qwen3.7-plus. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to qwen3.7-plus deliberately rather than by default.
Tags: qwen3.6-flash — Chat, Reasoning, Coding, Vision · qwen3.7-plus — Chat, Reasoning, Coding, Vision
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# qwen3.6-flash
client.chat.completions.create(model="qwen3.6-flash", messages=[{"role":"user","content":"Hi"}])
# qwen3.7-plus
client.chat.completions.create(model="qwen3.7-plus", messages=[{"role": "user", "content": "Hi"}])