Access DeepSeek, Kimi, GLM, Qwen and more through a single OpenAI-compatible endpoint. Token-level metering, transparent pricing, no vendor lock-in.
Drop-in replacement for the OpenAI SDK — just change the base URL and key.
Pay as you go. USD per 1M tokens. Free tier available on select models.
| Model | Input | Output | |
|---|---|---|---|
| Loading… | |||
Any app that supports a custom OpenAI endpoint works with ShunduAI — three fields and you're done.
https://shunduai.com/api/v1
sk-hk-… (from your console)
deepseek-v4-flash, glm-4.5-air, kimi-k2.6 …
Settings → Model Provider → OpenAI-compatible. Paste the Base URL and API key above, add a model name, done.
Settings → Custom endpoint → Base URL + API key. You get a full chat web app powered by ShunduAI.
Use the ChatOpenAI class with base_url pointed at ShunduAI. All frameworks work out of the box.
Works with the OpenAI SDK, LangChain, and any tool that accepts a custom base URL. Switch models with one parameter.
Latency-aware dispatch and automatic failover keep your app online even when a provider rate-limits or degrades.
Per-token metering with a real-time usage dashboard. Top up any amount, no subscriptions, no hidden fees.