<!-- GENERATED BY scripts/gen_markdown_twins.py; source: guides/index.html -->

# Use Chinese AI models in the tools you already run.

> Set up Cursor, Cline, LiteLLM, LobeChat, and n8n with ChinaAPI for OpenAI-compatible access to DeepSeek, Kimi, Qwen, GLM, and MiniMax models.

- Canonical page: https://chinaapi-ru.com/guides/
- Human-readable page: https://chinaapi-ru.com/guides/
- Live pricing: https://dash.chinaapi-ru.com/pricing?utm_source=chinaapi&utm_medium=markdown&utm_campaign=guides

ChinaAPI gives international developers one OpenAI-compatible endpoint for DeepSeek, Kimi, Qwen, GLM, and MiniMax models, billed in USD at gateway-synchronized token rates that may follow providers' official China list prices where configured.

[Start free — $2 credit](https://dash.chinaapi-ru.com/register?utm_source=chinaapi&utm_medium=web&utm_campaign=guides)

[Live model pricing](https://dash.chinaapi-ru.com/pricing)

## Five OpenAI-compatible integration paths.

[Cursor with Chinese models Configure Cursor's OpenAI API key and custom base URL for DeepSeek, Kimi, Qwen, and GLM coding workflows.](https://chinaapi-ru.com/guides/cursor/)

[Cline with Chinese models Use the OpenAI Compatible provider in the VS Code agent with ChinaAPI model IDs.](https://chinaapi-ru.com/guides/cline/)

[LiteLLM with Chinese models Route LiteLLM proxy and SDK calls through ChinaAPI using `openai/<model>` entries and `api_base`.](https://chinaapi-ru.com/guides/litellm/)

[LobeChat with Chinese models Set the OpenAI provider endpoint to ChinaAPI for chat access to Chinese LLM families.](https://chinaapi-ru.com/guides/lobechat/)

[n8n with Chinese models Create OpenAI credentials with a custom base URL and use them in AI Agent or OpenAI LLM nodes.](https://chinaapi-ru.com/guides/n8n/)

## Same endpoint across tools.

### Base URL

`https://api.chinaapi-ru.com/v1`. Chat completions are available at `/v1/chat/completions`.

### API key

Register, open Dashboard, then go to Console -> Tokens. Keys use the `sk-...` format.

### Trial

Signup includes $2 free credit for self-serve testing.

### Pricing

Check [live pricing](https://dash.chinaapi-ru.com/pricing) before production runs. Model availability and IDs can change.

## Create one key and reuse it across the guides.

Use the same ChinaAPI token in Cursor, Cline, LiteLLM, LobeChat, n8n, or direct OpenAI-compatible SDK calls.

[Register — $2 credit](https://dash.chinaapi-ru.com/register?utm_source=chinaapi&utm_medium=web&utm_campaign=guides)

[Live pricing](https://dash.chinaapi-ru.com/pricing)

### Good first models

`deepseek-v4-flash`, `qwen3.6-flash`, and `MiniMax-M2.7` are sensible low-latency first tests.

### Heavier reasoning

Try `qwen3.7-max`, `glm-5.2`, `deepseek-v4-pro`, or `kimi-k2.7-code` when output quality matters more than speed.

---

Markdown twin of https://chinaapi-ru.com/guides/ — generated from its canonical HTML by scripts/gen_markdown_twins.py. Full site reference: https://chinaapi-ru.com/llms-full.txt