# Free AI coding API: Cline, Continue, Aider and Cursor setup (markdown mirror)

Source: https://aiapi-pro.com/blog/free-ai-coding-api-cline-continue-aider-cursor

All four tools speak the OpenAI API format and need the same three values:

| Setting | Value |
|---|---|
| Base URL | `https://aiapi-pro.com/v1` |
| API key | from https://aiapi-pro.com/register (starts with `nvai-`) |
| Model id | `glm-4.7-flash` (free, 202K) or `glm-4.1v-thinking-flash` (free, reasoning) |

## Cline

1. Settings -> API Provider -> **OpenAI Compatible**
2. Base URL: `https://aiapi-pro.com/v1`
3. API Key: `nvai-...`
4. Model ID: `glm-4.7-flash`

## Continue

`config.yaml`:

```yaml
name: My Config
version: 0.0.1
schema: v1

models:
  - name: GLM-4.7-Flash (free)
    provider: openai
    model: glm-4.7-flash
    apiKey: <YOUR_NOVAI_KEY>
    apiBase: https://aiapi-pro.com/v1/
```

## Aider

```bash
export OPENAI_API_BASE=https://aiapi-pro.com/v1
export OPENAI_API_KEY=nvai-...
aider --model openai/glm-4.7-flash
```

## Cursor

1. Settings -> Models -> OpenAI API Key: `nvai-...`
2. Enable **Override OpenAI Base URL**: `https://aiapi-pro.com/v1`
3. Add custom model: `glm-4.7-flash`

## Which free model

| Model | Context | Use for |
|---|---|---|
| `glm-4.7-flash` | 202K | Everyday edits, refactors, multi-file changes |
| `glm-4.1v-thinking-flash` | 128K | Harder bugs with visible reasoning |

Free tier: 10 free-model calls/day, 5 requests/min, no card. When the cap is hit: HTTP 429 until 00:00 UTC+8; a one-time top-up removes the cap (60 req/min) and the first top-up carries a 25% bonus.

## FAQ

**Which free model should I use for coding?**
GLM-4.7-Flash (202K context) for general coding and edits; GLM-4.1V-Thinking-Flash (128K) when you want visible reasoning steps for harder problems. Both are free to call, capped at 10 free-model calls per day on the free tier.

**Does the free tier work with Cline, Continue, Aider and Cursor?**
Yes. All four support an OpenAI-compatible endpoint. Point the base URL at https://aiapi-pro.com/v1, use an nvai- key, and pick one of the five free model ids.

**What happens when the daily free cap is reached?**
Requests to free models return HTTP 429 until 00:00 UTC+8. A one-time top-up removes the free-tier cap and raises the rate limit to 60 requests per minute; the first top-up carries a 25% bonus.

**Can I use paid models in the same tool config?**
Yes. Add more entries with paid model ids (for example deepseek-v4-flash or kimi-k2.7-code) using the same base URL and key. Paid models are billed per token at provider list price with no platform markup.