AI Providers & Models
Configure providers, pick models, and control reasoning behavior
Overview
Quanta integrates with multiple AI providers so you can select the optimal combination of price, latency, and reasoning ability. Provider and model selection happens in the extension popup.
Supported Providers
API Key Storage
Keys are stored locally in your browser. Switching providers preserves previously entered keys for seamless transitions.
Dynamic Model Fetching
Quanta fetches live model lists from OpenAI and OpenRouter and caches them to reduce API calls and avoid rate limits.
Model list not updating?
Close and reopen the popup, verify your API key, or manually enter a model ID in the custom field.
Custom Model IDs (OpenRouter)
Use the custom field to access premium models not shown in the default free list.
deepseek/deepseek-r1-0528:freeGemini Reasoning Effort
Gemini provider exposes a reasoning effort control for tailored performance:
| Setting | Use Case | Best For |
|---|---|---|
| Auto | Balanced default | General questions |
| Off | Fastest simple lookup | Quick facts |
| Low | Slightly deeper logic | Simple reasoning |
| Medium | Multi-step reasoning without large latency | Standard quizzes |
| High | Maximum depth for complex questions | Difficult/ambiguous questions |
Increase the level if answers feel shallow or inconsistent on complex quizzes.
Provider Selection Strategy
| Provider | Strengths | Considerations | Best Use Case |
|---|---|---|---|
| Gemini | Fast + reasoning control | Requires tuning effort level | Speed-critical tasks |
| OpenAI | Strong general accuracy | Higher cost for top models | Complex reasoning |
| Anthropic | Long context & nuanced reasoning | Slightly slower for small tasks | Detailed analysis |
| Perplexity | Web-informed answers | May include external search latency | Current information |
| OpenRouter | Flexibility & variety | Model quality varies per vendor | Cost optimization |
Handling Failures
Quanta implements improved error handling (1.4.x) with graceful recovery.
Performance Tips
Pro Tip
Combine provider selection with Bulk Answering settings to find your optimal cost-latency-quality balance.
Security Notes
API keys are stored locally in your browser extension storage and are never transmitted except to your chosen AI provider's API. No server-side storage or logging occurs.
Next Steps
Configure Bulk Answering and Session Memory to complement your provider setup.
Last updated on