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

# Use Cline with Chinese AI models through ChinaAPI.

> Configure Cline in VS Code with the OpenAI Compatible provider and ChinaAPI model IDs for DeepSeek, Kimi, Qwen, GLM, and MiniMax.

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

Configure Cline's OpenAI Compatible provider once, then run agentic VS Code workflows on official-price Chinese models with one ChinaAPI key.

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

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

## What you need.

### Cline extension

Install Cline in VS Code and open the Cline panel.

### ChinaAPI token

Register, then go to Dashboard -> Console -> Tokens and copy an `sk-...` key.

## Configure the OpenAI Compatible provider.

- Open the Cline settings panel from the gear icon or the API Provider dropdown below the chat area.

- Set **API Provider** to **OpenAI Compatible**.

- Set **Base URL** to `https://api.chinaapi-ru.com/v1`.

- Paste your ChinaAPI token into **API Key**.

- Set **Model** or **Model ID** to an exact live ID such as `kimi-k2.7-code` or `deepseek-v4-pro`.

- Click **Verify** if your Cline version exposes that button, then send a short test message.

## Test with a tiny Cline prompt.

After saving the provider, ask Cline:

```
Create a minimal Node.js function called summarizeFiles(paths) that returns file names and byte sizes. Do not modify files yet.
```

For a direct API smoke test, use:

```
curl https://api.chinaapi-ru.com/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"kimi-k2.7-code","messages":[{"role":"user","content":"Say Cline is connected."}],"stream":true}'
```

## Good Cline 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 Pro](https://chinaapi-ru.com/models/deepseek-v4-pro/) before choosing a production default.

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

Coding-focused default for repo work, planning, and edits.

### `deepseek-v4-pro`

Use for harder debugging, refactors, and reasoning-heavy coding tasks.

### `qwen3.7-max`

Flagship Qwen option for demanding analysis and agent workflows.

### `glm-5.2`

Strong long-context choice for larger codebase understanding.

### `deepseek-v4-flash`

Fast option for quick iterations and lighter Cline tasks.

## Common Cline issues.

Thinking models such as `qwen3.7-max` can spend time generating reasoning tokens before answering. Enable streaming or raise the request timeout if Cline stops before the answer arrives.

**Model not found:** copy the exact ID from [live pricing](https://dash.chinaapi-ru.com/pricing). Do not use display names like "DeepSeek V4" unless the pricing page shows that exact ID.

**401:** make sure the key starts with `sk-` and is in the API Key field for the OpenAI Compatible provider, not another provider profile.

## Start with $2 free credit.

ChinaAPI bills token usage in USD using gateway-synchronized rates, which may follow providers' official China list prices where configured. Check live pricing before production use.

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

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

---

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