Choosing Models

Agentastic supports multiple AI models, each optimized for different tasks. Understanding which model to use and when will help you get the best performance and results.

Model Types

Agentastic categorizes models into six capability types, each optimized for different tasks:

Chat Models 💬

General-purpose conversational models for everyday tasks:

• Best for: Quick queries, text generation, casual conversations
• Speed: Fast response times
• Tools: Limited tool access
• Examples: Agentastic, Claude Haiku, Gemini Flash

When to use: Default choice for most interactions, simple text expansions, quick questions.

Vision Models 👁

Models that can understand and analyze images:

• Best for: Screenshot analysis, image descriptions, visual Q&A
• Speed: Moderate response times
• Tools: Standard tools plus image processing
• Examples: Agentastic, Claude Sonnet, Gemini Pro

When to use: Analyzing screenshots, understanding diagrams, extracting text from images.

Agent Models ∞

Advanced models with reasoning and tool-use capabilities:

• Best for: Complex tasks, multi-step workflows, tool integration
• Speed: Slower but more capable
• Tools: Full access to all tools (calendar, email, search, files)
• Examples: Agentastic, Claude Opus, GPT-5, Qwen3 Max

When to use: Complex research, calendar management, email composition, file operations.

Automation Models 🖱️

Specialized models for desktop control and automation:

• Best for: GUI automation, desktop control, system tasks
• Speed: Variable depending on task
• Tools: Desktop control, mouse/keyboard automation
• Examples: Agentastic, Claude Sonnet

When to use: Automating repetitive desktop tasks, UI testing, complex workflows.

Thinking Models 🧠

Models with advanced reasoning and "thinking" capabilities:

• Best for: Deep reasoning, complex problem-solving, multi-step analysis
• Speed: Slower due to extended reasoning
• Tools: Full tool access with enhanced reasoning
• Examples: OpenAI O3, DeepSeek R1, Qwen3 Thinking, Claude Opus

When to use: Complex problem-solving, research requiring deep reasoning, multi-step analysis.

Image Generation Models 🎨

Models that can generate and edit images:

• Best for: Creating images from text, image editing
• Speed: Variable depending on complexity
• Tools: Image generation and editing
• Examples: Agentastic Imagine, Gemini Banana, Hunyuan v3, SeeDream v4

When to use: Creating images from descriptions, editing existing images, visual content generation.

Available Models

Agentastic Recommended Models 💜

These are Agentastic's optimized models, recommended for most users:

OpenAI Models

Anthropic (Claude) Models

Google Models

Gemini 3 update (Nov 18, 2025)

• Launch blog highlights that Gemini 3 Pro now tops major benchmarks (1501 Elo on LMArena, 81% on MMMU-Pro, 87.6% on Video-MMMU, 72.1% on SimpleQA Verified) and introduces a Deep Think mode that reaches 41% on Humanity's Last Exam (no tools) and 45.1% on ARC-AGI-2 with code execution. Deep Think is rolling out to Gemini Ultra subscribers after safety testing.
• The Gemini 3 API guide documents the gemini-3-pro-preview model ID, a 1M input / 64K output window, a Jan 2025 knowledge cutoff, and pricing of $2 / $12 per 1M tokens below 200K tokens ($4 / $18 after). It also introduces the thinking_level parameter (low for lower latency/cost, high default for Deep Think depth, with medium coming soon) and the new media_resolution_{low|medium|high} knobs: images default to 1120 tokens at high, PDFs saturate at 560 tokens with medium, and video frames cost 70 tokens at low/medium (280 tokens if you force high for dense OCR).
• Gemini 3 Pro does not yet support pixel-level segmentation; keep /model:flash (Gemini 2.5 Flash with thinking disabled) or Gemini Robotics-ER 1.5 for those workloads per Google's guidance.

DeepSeek Models

Grok Models (x-ai)

Qwen Models

Meta (Llama) Models

Other Providers

Image Generation Models

Model Selection

Quick Selection in Launcher

Use the /model: tag to quickly switch models:

1. Type /model: in the launcher
2. Browse available models with arrow keys
3. Select with Enter or click
4. Continue with your prompt

Example:

/model:opus Analyze this research paper and summarize key findings
/model:agent What's on my calendar today?
/model:agent What do you see in this screenshot?

Setting Default Models

Configure your preferred models in Settings:

1. Open Settings (⌘,)
2. Go to Models and Providers
3. Set defaults for each role:
   • The default agent model (used for chat and agent work)
   • Default Fast Model
   • Default Vision Model
   • Default Computer (automation) Model
   • Default Image Model
   • Default Dictation Model
   • Default Bundle (comparison) Model

Model-Specific Tags

Some tags automatically suggest appropriate models:

• /vision - Activates vision-capable models
• /agent - Enables agent mode with tool access
• /automation - Uses automation-capable models
• /imagine - Uses image generation models

Configuration

Models Configuration File

Advanced users can customize models in ~/Library/Application Support/agentastic/config/models.yml:

active_models:
  - value: agentastic:agent
    label: Agentastic 💜
    description: Designed for advanced agentic tasks
    context_length: 1050000
    output_max_tokens: 128000
    capabilities:
      - agent
      - chat
      - vision
      - thinking
      - automation
      - dictation
    fallback_model: agentastic:sonnet

  - value: agentastic:fast
    label: Agentastic Fast 💜
    description: Fast route for quick responses
    context_length: 1050000
    output_max_tokens: 128000
    capabilities:
      - chat
      - fast
      - agent
      - vision
      - thinking
      - dictation
    fallback_model: agentastic:haiku

API Keys

Configure credentials in Settings → Models and Providers. Agentastic has first-class support for three providers:

• Agentastic: included with your plan, no key required
• Anthropic: API key (sk-ant-…) or sign in with your Claude subscription
• OpenAI: API key (sk-…) or sign in with your ChatGPT subscription

Models from other vendors (Google, xAI, DeepSeek, Qwen, and more) are available through the Agentastic provider's routing. See Configuring Providers for the full flow.

Security note: Credentials are stored securely on your device.

Model Selection Strategy

For Different Tasks

Writing Emails

• Quick email: Agentastic Fast, Gemini Flash, Claude Haiku
• Important email: Agentastic, Claude Sonnet, GPT-5.6
• Complex negotiation: Claude Opus, Qwen3 Max

Research & Analysis

• Quick fact check: Agentastic Fast, Gemini Flash
• Deep research: Claude Opus, Qwen3 Max with /agent
• Visual analysis: Agentastic, Gemini Pro, Qwen 3.8 Max

Code & Technical

• Quick snippets: Agentastic Fast, Gemini Flash
• Complex debugging: Qwen 3.8, Grok 4.6, Claude Opus
• Code review: Claude Sonnet, Agentastic

Automation

• Simple tasks: Agent models with tools
• Desktop control: Agentastic
• Multi-step workflows: Agentastic, Claude Opus with /agent

Performance vs. Quality

Balance speed and capability based on your needs:

Fast Response Needed → Agentastic Fast, Gemini Flash, Claude Haiku

Balanced Performance → Agentastic, Claude Sonnet, GPT-5.6 Terra, Gemini 3.1 Pro

Best Quality → Claude Opus, GPT-5, Qwen3 Max, OpenAI O3

Special Capabilities → Vision models for images (Agentastic, Qwen 3.8 Max), the default Agent model for desktop control, reasoning-capable models for deep analysis, and Agentastic Imagine for image generation

Cost Considerations

Different models have different pricing:

Cost Tiers (Relative)

1. Low Cost: Agentastic Fast, Claude Haiku, Gemini Flash Lite (for quick tasks)
2. Medium Cost: Agentastic, Claude Sonnet, Gemini Flash
3. Higher Cost: Claude Opus, GPT-5, Gemini 3 Pro (Preview), Qwen3 Max, Agentastic
4. Specialized: Automation models, Thinking models, Image generation models (variable)

Optimizing Costs

1. Use appropriate models: Don't use Opus for simple tasks
2. Leverage chat mode: Agent mode uses more tokens
3. Clear context: Start new conversations when context isn't needed

Model Limitations

Context Windows

Different models have different context limits:

• Small (8K-65K): OpenAI Computer Use (8K), GLM Vision (65K)
• Standard (128K-131K): Most models including GPT-5, GPT-4o, DeepSeek
• Large (200K-1.05M): Agentastic (1.05M), Claude models (up to 1M), Grok models (up to 500K), Qwen 3.8 models (up to 1.05M)
• Very Large (262K): Qwen3 Thinking, Qwen3 Next models
• Massive (1M+): Google Gemini 3 Pro (Preview) / Gemini 2.5 Flash (1M tokens), Grok 4 Fast (2M tokens)

Rate Limits

API providers impose rate limits:

• Per minute: Number of requests
• Per day: Total token usage
• Concurrent: Parallel requests

Agentastic automatically manages rate limits and queues requests when necessary.

Feature Support

Not all models support all features:

*Depends on specific model

Troubleshooting

Model Not Available

If a model isn't showing up:

1. Check API key is configured
2. Verify internet connection
3. Check provider service status
4. Ensure model is enabled in settings

Poor Results

If a model isn't performing well:

1. Try a more capable model
2. Use appropriate tags (/agent, /vision)
3. Provide clearer prompts
4. Add relevant context via memory channels

Rate Limit Errors

If you hit rate limits:

1. Wait for the reset period (usually 1 minute)
2. Switch to a different model
3. Reduce request frequency
4. Consider upgrading API tier

Best Practices

1. Start with Agentastic or another recommended model for most tasks
2. Use vision models only when analyzing images
3. Enable agent mode when you need tools
4. Reserve automation models for desktop tasks
5. Use thinking models for complex reasoning problems
6. Use image generation models for creating visual content
7. Test different models to find what works best for your workflow
8. Monitor usage to optimize costs

What's Next?

Now that you understand models:

• Configuring Providers - Connect Anthropic, OpenAI, and Agentastic
• Commands & Tags - Master special tags
• Advanced Settings - Fine-tune configuration
• Troubleshooting - Solve common issues

Pro Tip: Use /model: frequently to experiment with different models. You'll quickly learn which models work best for your specific use cases.