通义千问 3 代旗舰, 长上下文能力增强, 含隐式+显式 cache.
Model ID: qwen3-max · Type: chat · Provider: Alibaba
Endpoints: /v1/chat/completions · /v1/messages · /v1/responses
| Input (per 1M tokens) | $0.72 USD |
| Output (per 1M tokens) | $3.6 USD |
| Cache read implicit (per 1M tokens) | $0.144 USD |
| Cache read explicit (per 1M tokens) | $0.072 USD |
| Cache write 5m (per 1M tokens) | $0.9 USD |
| ≤ 32000 tokens | $0.72 / 1M in | $3.6 / 1M out |
| ≤ 128000 tokens | $1.44 / 1M in | $7.2 / 1M out |
| > 128000 | $1.8 / 1M in | $9 / 1M out |
import os
from openai import OpenAI
client = OpenAI(api_key=os.environ["ROUTER_API_KEY"], base_url="https://api.router.ai/v1")
resp = client.chat.completions.create(
model="qwen3-max",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)Qwen3-Max (`qwen3-max`) is billed per usage at $0.72/1M in · $3.6/1M out, in USD. Current pricing is always listed at https://opencrow.ai/models/qwen3-max.
Send a request to https://api.router.ai/v1/chat/completions with the header `Authorization: Bearer <your API key>` and `"model": "qwen3-max"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.
Qwen3-Max can be called on: /v1/chat/completions; /v1/messages; /v1/responses.
Qwen3-Max is a chat model from Alibaba, available through the OpenCrow gateway with the same API key as every other model.
Call it through the OpenCrow OpenAI-compatible endpoint (API base: https://api.router.ai/v1). AI agents can browse the catalog and call any text model through MCP (https://mcp.router.ai/mcp); for image, video and other modalities use the API above.