Choosing an AI Model
Compare AI models available in Firebuzz and learn which one to use for your tasks.
Firebuzz gives you access to 12 AI models from leading providers. Each model has different strengths in terms of cost, speed, and intelligence. Choosing the right model helps you work efficiently while managing costs.
Available Models
Recommended
| Model | Provider | Cost | Speed | Intelligence | Best For |
|---|---|---|---|---|---|
| Auto | Firebuzz | Low | Fast | High | General use — let Firebuzz choose the best model |
| Minimax M2 | Minimax | Low | Fast | High | Best balance of cost, speed, and quality |
Anthropic (Claude)
| Model | Cost | Speed | Intelligence | Best For |
|---|---|---|---|---|
| Claude Haiku 4.5 | Low | Fast | Medium | Quick tasks and simple edits |
| Claude Sonnet 4.5 | High | Medium | Highest | Complex design work and detailed changes |
| Claude Opus 4.5 | Highest | Medium | Highest | Most demanding tasks requiring maximum intelligence |
OpenAI (GPT)
| Model | Cost | Speed | Intelligence | Best For |
|---|---|---|---|---|
| GPT-5.1 Codex Max | Medium | Medium | High | Technical changes and code-heavy tasks |
| GPT-5.2 | Medium | Medium | High | Reasoning and analytical tasks |
| GPT-5.1 Codex Mini | Low | Fast | Medium | Faster and cheaper OpenAI model |
Google (Gemini)
| Model | Cost | Speed | Intelligence | Best For |
|---|---|---|---|---|
| Gemini 2.5 Pro | Medium | Medium | High | Research-heavy tasks with long context |
| Gemini 3 Flash | Low | Fastest | Medium | Fast and affordable Google model |
| Gemini 3 Pro Preview | High | Fast | Highest | Google's latest preview model with highest intelligence |
Other Providers
| Model | Provider | Cost | Speed | Intelligence | Best For |
|---|---|---|---|---|---|
| Kimi K2 Thinking Turbo | MoonshotAI | Low | Fast | High | Fast thinking model with reasoning capabilities |
| Kimi K2 Thinking | MoonshotAI | Low | Medium | High | Thinking model with reasoning capabilities |
How to Switch Models
- Look for the model button in the chat input area (shows current model name, e.g., Auto)
- Click it to open the model selector
- Search by model name or provider
- Review cost, speed, and intelligence indicators
- Click a model to select it
Each model displays three indicators: Cost (how many credits it uses), Speed (how fast it responds), and Intelligence (how capable it is for complex tasks). More filled dots means higher in that category.
Model Recommendations
Just Getting Started
Use Auto or Minimax M2. These provide excellent results for most tasks while being cost-effective.
Complex Design Work
Use Claude Sonnet 4.5. It excels at understanding design requirements and making sophisticated changes.
Need Speed
Use Gemini 3 Flash. It's the fastest model available, ideal when you're iterating quickly.
Technical Tasks
Use GPT-5.1 Codex Max. It's optimized for code generation and technical modifications.
Understanding the Indicators
Cost
- Low — Uses fewer credits per message
- Medium — Moderate credit usage
- High/Highest — Uses more credits per message
Speed
- Medium — Standard response time
- Fast — Quick responses
- Fastest — Near-instant responses
Intelligence
- Medium — Good for straightforward tasks
- High — Capable of complex reasoning
- Highest — Best for demanding, nuanced tasks