docs/core-features/model-selection-guide.mdx
New models drop constantly, so this guide focuses on what's working well with Cline right now. We'll keep it updated as the landscape shifts.
<Callout type="tip"> **New to model selection?** Start with [Module 2 of Cline's Learning Path](https://cline.bot/learn) for a comprehensive guide to choosing and configuring models. </Callout>Think of an AI model as the "brain" that powers Cline. When you ask Cline to write code, fix bugs, or refactor your project, it's the model that actually understands your request and generates the response.
Key points:
Why it matters: The model you choose directly impacts Cline's capabilities, response quality, speed, and cost. A premium model might handle complex refactoring beautifully but cost more, while a budget model works great for routine tasks at a fraction of the price.
Follow these 5 simple steps to get Cline up and running with your preferred AI model:
First, you need to access Cline's configuration panel.
Two ways to open settings:
The settings panel will open, showing configuration options with "API Provider" at the top.
<Note> The settings panel remembers your last configuration, so you'll only need to set this up once. </Note>Choose your preferred AI provider from the dropdown menu.
<Frame> </Frame>Popular providers at a glance:
| Provider | Best For | Notes |
|---|---|---|
| Cline | Easiest setup | No API keys needed, access to multiple models including stealth models |
| OpenRouter | Value seekers | Multiple models, competitive pricing |
| Anthropic | Reliability | Claude models, most dependable tool usage |
| OpenAI | Latest tech | GPT-5, o3, o4-mini models |
| OpenAI Codex | ChatGPT subscribers | Use your ChatGPT subscription — no API key needed |
| Google Gemini | Large context | Gemini 3/2.5 with up to 2M context |
| DeepSeek | Budget reasoning | V3.2, R1 models at low cost |
| Alibaba Qwen | Open source coding | Qwen3 Coder with 1M context |
| Moonshot | Agentic coding | Kimi K2.5 with 262K context |
| Cerebras | Speed | Up to 2,600 tokens/sec |
| AWS Bedrock | Enterprise | Advanced features |
| Ollama | Privacy | Run models locally |
See the full provider list for all 30+ supported providers including xAI Grok, Mistral, Groq, Fireworks, Together, Baseten, SambaNova, Nebius, Hugging Face, and more.
<Info> **Recommended for beginners:** Start with **Cline** as your provider - no API key management needed, instant access to multiple models, and occasional free inferencing through partner providers. </Info>The next step depends on which provider you selected.
See the full OpenAI Codex setup guide for details.
You'll need to get an API key from your chosen provider:
Visit your provider's website to get an API key:
Generate a new API key on the provider's website
Copy the API key to your clipboard
Paste your key in the "API Key" field in Cline settings
Save automatically - Your key is stored securely in your editor's secrets storage
Once your API key is added (or you've signed in), the "Model" dropdown becomes available.
<Frame> </Frame>Quick model selection guide:
| Your Priority | Choose This Model | Why |
|---|---|---|
| Maximum reliability | Claude Sonnet 4.5 | Most reliable tool usage, excellent at complex tasks |
| Best value | DeepSeek V3 or Qwen3 Coder | Great performance at budget prices |
| Fastest speed | Qwen3 Coder on Cerebras | Lightning-fast responses |
| Run locally | Any Ollama model | Complete privacy, no internet needed |
| Latest features | GPT-5 | OpenAI's newest capabilities |
Not sure which to pick? Start with Claude Sonnet 4.5 for reliability or DeepSeek V3 for value.
<Tip> You can switch models at any time without losing your conversation. Try different models to find what works best for your specific tasks. </Tip>See the model comparison tables below for detailed specifications and pricing.
Congratulations! You're all set up. Here's how to start coding with Cline:
Type your request in the Cline chat box
Press Enter or click the send icon to submit
Selecting the right model involves balancing several factors. Use this framework to find your ideal match:
<Note> **Pro tips**: Configure separate models for Plan Mode and Act Mode. Make the most out the each model's strengths. For example, use a budget model for planning discussions and a premium model for implementation. </Note>| Factor | What to Consider | Recommendation |
|---|---|---|
| Task Complexity | Simple fixes vs complex refactoring | Budget models for routine tasks; Premium models for complex work |
| Budget | Monthly spending capacity | $10-$30: Budget, $30-$100: Mid-tier, $100+: Premium |
| Context Window | Project size and file count | Small: 32K-128K, Medium: 128K-200K, Large: 400K+ |
| Speed | Response time requirements | Interactive: Fast models, Background: Reasoning models OK |
| Tool Reliability | Complex operations | Claude excels at tool usage; Test others with your workflow |
| Provider | Access and pricing needs | OpenRouter: Many options, Direct: Faster/reliable, Local: Privacy |
For detailed model comparisons and performance metrics, see:
| If you want... | Use this |
|---|---|
| Something that just works | Claude Sonnet 4.5 |
| To save money | DeepSeek V3 or Qwen3 variants |
| Huge context windows | Gemini 2.5 Pro or Claude Sonnet 4.5 |
| Open source | Qwen3 Coder, Z AI GLM 4.5, or Kimi K2 |
| Latest tech | GPT-5 |
| To use your ChatGPT subscription | OpenAI Codex — sign in with your OpenAI account, no API key needed |
| Speed | Qwen3 Coder on Cerebras (fastest available) |
Check Vercel's leaderboard to see real usage patterns from the community.