Qwen3-Max-32K API
Use Qwen3-Max-32K via TokenDock API. Input: $0.2154 / 1M tokens, Output: $0.8580 / 1M tokens. OpenAI-compatible endpoint.
Pricing
| Direction | TokenDock Price | Provider List Price |
|---|---|---|
| Input (per 1M tokens) | $0.2154 / 1M tokens | $0.3590 / 1M tokens |
| Output (per 1M tokens) | $0.8580 / 1M tokens | $1.4340 / 1M tokens |
| Context window | 32K tokens | |
Quick Start
TokenDock is OpenAI-compatible. Set base_url and model, and your existing OpenAI SDK code works unchanged.
Python
from openai import OpenAI
client = OpenAI(
api_key="your-tokendock-api-key",
base_url="https://tokendock.ai/v1",
)
response = client.chat.completions.create(
model="qwen3-max-32k",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)See also
Browse all available models · Pricing overview · Create account