Use DeepSeek V4.1 Flash in Cline

Steps

1. Install and open settings. Install Cline in VS Code and open its settings panel with the gear icon.
2. Choose the provider. Set API Provider to OpenAI Compatible.
3. Set the endpoint. Base URL: https://api.fikraapi.co.ke/v1
4. Add the key. API Key: your fk_live_ key from the dashboard.
5. Set the model. Model ID: deepseek-v4.1-flash-1017
6. Save and run. Save the settings and start a task. Cline sends a normal OpenAI chat-completions request.

Base URL: https://api.fikraapi.co.ke/v1
API Key: YOUR_FIKRA_KEY
Model ID: deepseek-v4.1-flash-1017

Run a one-line task in Cline, such as: explain what this file does.

Default model: deepseek-v4.1-flash-1017. Prices come from the live catalog.

Repeated prompt prefixes are billed at the cached rate. Cached input can never cost more than fresh input.

While the window is open, model deepseek-v4-1-flash-economy-free is free. Check live availability.

Troubleshooting

The key is missing, revoked, or has a leading space. Paste it again from the dashboard and use the fk_live_ value.

The base URL usually has an extra /chat/completions. Use exactly https://api.fikraapi.co.ke/v1.

The model ID is case sensitive. Copy it from /models or the snippet on the dashboard.

You hit the account rate limit. Free accounts allow 30 requests per minute and 300 per day. Any top-up raises the limits.