Cline account
Sign in with Google, GitHub, or email. No API keys to manage. Access models from Anthropic, OpenAI, Google, and more through a single account with built-in billing.Best for: Most users, fastest setup.
Bring your own key (BYOK)
Paste an API key from any supported provider: Anthropic, OpenRouter, OpenAI, Google Gemini, AWS Bedrock, and more. Run models locally with Ollama or LM Studio for full privacy.Best for: Enterprise, custom billing, local models.
Sign in with a Cline account
The Cline account gives you access to multiple AI models through a single login — no separate API keys required.Open the Cline panel
Click the Cline icon in the Activity Bar (VS Code/Cursor) or go to View → Tool Windows → Cline (JetBrains).
Click Sign Up
In the Cline panel, click Sign Up. Your browser opens to app.cline.bot.
Return to your editor
After authentication, you are redirected back to your editor. Cline stores your session token in your IDE’s native secret storage (VS Code Secrets or JetBrains Credential Store). Your credentials are never sent to Cline’s servers.
Select a model
Open Cline settings (gear icon in the Cline panel). Under API Provider, make sure Cline is selected. Then choose a model from the Model dropdown.To find no-cost options, search for free in the model selector — free models are labeled FREE.
Adding credits: Click Add Credits in Cline settings or visit your account dashboard. Credits work across all available models.
Bring your own API key (BYOK)
If you prefer to use your own API keys — for specific billing arrangements, higher rate limits, or access to beta models — select your provider in Cline settings and paste your key.Paste your API key
Enter your API key in the field provided. Keys are stored in your system’s credential manager and sent only to your selected provider — never to Cline’s servers.
Provider setup
- Anthropic
- OpenRouter
- OpenAI
- Google Gemini
- AWS Bedrock
Anthropic provides direct access to Claude models including Claude Sonnet and Claude Opus.Get an API key:
- Go to console.anthropic.com.
- Sign in or create an account.
- Navigate to API Keys and click Create Key.
- Copy the key — it starts with
sk-ant-.
- API Provider: Anthropic
- API Key: Paste your key
- Model: Choose from available Claude models (Claude Sonnet 4 is recommended for reliability)
Local models
Run models on your own hardware for complete privacy and zero per-request cost.Ollama
Easy setup with a wide model selection. Supports Llama, Qwen, Mistral, and many others. Run
ollama serve and select Ollama in Cline settings.LM Studio
GUI-based model management and download. Start the local server in LM Studio and select LM Studio as your provider in Cline settings.
Local models require sufficient hardware, particularly GPU memory. Smaller models (7B–14B parameters) work on consumer hardware; larger models need more RAM or a GPU. See the running models locally guide for requirements.
Choosing a model
| Priority | Recommended model |
|---|---|
| Best overall reliability | Claude Sonnet 4 |
| Best value | Qwen3 Coder |
| Fastest responses | Cerebras GLM 4.6 |
| Full privacy | Any Ollama or LM Studio model |
| Existing Claude subscription | Claude Code (Max/Pro plan) |
CLI authentication
If you use the Cline CLI, authenticate from your terminal:Troubleshooting
| Issue | Fix |
|---|---|
| ”Unauthorized: Please sign in” | Session expired. Click Sign In in Cline settings to re-authenticate. |
| Browser doesn’t open for OAuth | Check your default browser settings. Copy the URL from the Cline output panel and open it manually. |
| Frequent re-authentication | Ensure you are not clearing IDE secrets. Try a full sign-out and sign-in. |
| API key not accepted | Verify the key is active and has not expired. Confirm you selected the matching provider in Cline settings. |
| Can’t access organization | Verify membership at app.cline.bot and ask your admin about permissions. Sign out and sign in again. |
Next steps
Your first project
Build a working todo app with Cline to practice the core workflow.
Model selection guide
Compare models across speed, cost, and context window size to find the best fit for your tasks.