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

# Use Cursor with Chinese AI models through ChinaAPI.

> Configure Cursor with ChinaAPI's OpenAI-compatible endpoint for DeepSeek, Kimi, Qwen, GLM, and MiniMax coding models.

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

Point Cursor at one OpenAI-compatible endpoint for cheap official-price Chinese coding models, including DeepSeek, Kimi, Qwen, GLM, and MiniMax families.

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

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

## Before opening Cursor settings.

### ChinaAPI account

Register, then open Dashboard -> Console -> Tokens to create or copy an `sk-...` API key.

### Endpoint

Use `https://api.chinaapi-ru.com/v1` as the OpenAI-compatible base URL.

## Configure Cursor.

- Open Cursor settings. In current versions this is usually Settings -> Models; naming can vary by release.

- Find the OpenAI API key area or the model provider section that accepts an OpenAI-compatible key.

- Paste your ChinaAPI key into the OpenAI API key field.

- Set the custom OpenAI base URL or override URL to `https://api.chinaapi-ru.com/v1`.

- Add one or more custom model IDs from the live pricing list, then select one for chat or agent mode.

## Verify the same key outside Cursor first.

```
curl https://api.chinaapi-ru.com/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      {"role": "user", "content": "Reply with exactly: Cursor is connected to ChinaAPI."}
    ],
    "stream": true
  }'
```

After the curl test works, ask Cursor: `Write a small TypeScript function that validates an email address.`

## Good Cursor defaults.

For current model details and rate evidence, review [Kimi K2.7 Code](https://chinaapi-ru.com/models/kimi-k2.7-code/) and [DeepSeek-V4 Flash](https://chinaapi-ru.com/models/deepseek-v4-flash/) before choosing a production default.

### `kimi-k2.7-code`

Coding-focused Kimi model for repo navigation, edits, and longer coding sessions.

### `deepseek-v4-pro`

Strong coding and reasoning model for harder refactors and analysis tasks.

### `qwen3.7-plus`

Balanced multimodal reasoning model for planning, tool use, and daily coding help.

### `qwen3.6-flash`

Fast, lower-latency choice for quick edits, summaries, and agent loops.

### `glm-5.2`

Long-context GLM model for larger codebase questions and agentic work.

## Common Cursor connection issues.

Thinking models such as `qwen3.7-max` can generate reasoning tokens before the answer appears. Enable streaming where Cursor exposes it, or raise the client timeout if requests end early.

**Model not found:** check the exact model ID on [live pricing](https://dash.chinaapi-ru.com/pricing). IDs are case-sensitive and may differ from public marketing names.

**401:** confirm the key starts with `sk-` and is sent as `Authorization: Bearer sk-...`. In Cursor, make sure the key is in the OpenAI key field tied to the custom base URL.

## Use gateway-synchronized token pricing from one USD account.

Token-model rates may follow providers' official China list prices where configured. Signup includes $2 free credit. Check live pricing before production runs because model IDs and availability can change.

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

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

---

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