Model Selection
Choose the right AI model for your needs
PaperPilot supports multiple AI model providers, giving you flexibility to choose the best model for your task.
Available Models
Google Gemini
| Model | Best For | Speed |
|---|---|---|
| Gemini 2.0 Flash | Fast responses, general tasks | ⚡⚡⚡ |
| Gemini 1.5 Pro | Complex reasoning, long documents | ⚡⚡ |
Gemini 2.0 Flash is the default and works well for most tasks. Switch to 1.5 Pro for very long documents or complex analysis.
OpenAI
| Model | Best For | Speed |
|---|---|---|
| GPT-4o | High-quality writing, nuanced edits | ⚡⚡ |
| GPT-4o Mini | Quick tasks, cost-effective | ⚡⚡⚡ |
Anthropic Claude
| Model | Best For | Speed |
|---|---|---|
| Claude 3.5 Sonnet | Academic writing, careful analysis | ⚡⚡ |
| Claude 3 Haiku | Fast responses, simple tasks | ⚡⚡⚡ |
Claude excels at following nuanced instructions and producing well-structured academic prose.
High-Speed Options
| Model | Provider | Best For |
|---|---|---|
| Llama 3.3 70B | Groq | Ultra-fast responses |
| Llama 3.1 8B | Cerebras | Near-instant responses |
These models run on specialized hardware for extremely low latency, perfect for quick iterations.
How to Change Models
Open Model Selector
Click the model name in the chat input area (shows current model).
Browse Available Models
A dialog opens showing all available models organized by provider.
Select Your Model
Click on any model to switch to it immediately.
Your model choice persists across sessions. Each conversation remembers which model you were using.
Choosing the Right Model
For Research Tasks
| Task | Recommended Model |
|---|---|
| Quick paper search | Gemini 2.0 Flash |
| Detailed paper analysis | Claude 3.5 Sonnet |
| Summarizing many papers | GPT-4o |
For Writing Tasks
| Task | Recommended Model |
|---|---|
| Drafting content | GPT-4o or Claude 3.5 |
| Quick edits | Gemini 2.0 Flash |
| LaTeX fixes | Any fast model |
| Final polish | Claude 3.5 Sonnet |
For Speed-Critical Tasks
When you need instant responses:
- Groq Llama — Best balance of speed and quality
- Cerebras Llama — Absolute fastest
- Gemini Flash — Good speed with Google's quality
Model Comparison
| Model | Quality | Speed | Context Window |
|---|---|---|---|
| GPT-4o | ⭐⭐⭐⭐⭐ | ⭐⭐⭐ | 128K tokens |
| Claude 3.5 Sonnet | ⭐⭐⭐⭐⭐ | ⭐⭐⭐ | 200K tokens |
| Gemini 2.0 Flash | ⭐⭐⭐⭐ | ⭐⭐⭐⭐ | 1M tokens |
| Gemini 1.5 Pro | ⭐⭐⭐⭐⭐ | ⭐⭐ | 2M tokens |
| Groq Llama 3.3 | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | 128K tokens |
Large Documents
For very large documents or projects, use Gemini models which have the largest context windows (up to 2M tokens).
Bring Your Own API Key
Want to use your own API keys for higher rate limits or billing control?
- Go to Settings → API Keys
- Enter your API key for the desired provider
- Your key is stored securely and used for your requests
Keep your API keys secure. Never share them or commit them to version control.