AI Models

Dialogix supports multiple AI providers, giving you flexibility in speed, quality, and cost.

Supported Providers

OpenAI

The industry-leading AI models from OpenAI.

Model	Best For	Speed	Quality
GPT-4o	Complex tasks, nuanced writing	⚡⚡⚡	⭐⭐⭐⭐⭐
GPT-4o Mini	Quick tasks, high volume	⚡⚡⚡⚡⚡	⭐⭐⭐⭐

Strengths: Excellent instruction following, strong reasoning, great for creative writing.

Google Gemini

Google's multimodal AI models.

Model	Best For	Speed	Quality
Gemini 2.0 Flash	Fast responses, general use	⚡⚡⚡⚡⚡	⭐⭐⭐⭐
Gemini 1.5 Pro	Complex analysis, long context	⚡⚡⚡	⭐⭐⭐⭐⭐

Strengths: Very fast, excellent for factual tasks, handles long documents well.

DeepSeek

Powerful models with strong reasoning capabilities.

Model	Best For	Speed	Quality
DeepSeek V3	General tasks, cost-effective	⚡⚡⚡⚡	⭐⭐⭐⭐
DeepSeek R1	Complex reasoning, analysis	⚡⚡⚡	⭐⭐⭐⭐⭐

Strengths: Excellent reasoning, very cost-effective, strong coding assistance.

xAI (Grok)

Elon Musk's AI models known for being direct and unfiltered.

Model	Best For	Speed	Quality
Grok 2	General conversation, analysis	⚡⚡⚡⚡	⭐⭐⭐⭐
Grok 2 Vision	Image understanding tasks	⚡⚡⚡	⭐⭐⭐⭐

Strengths: Real-time knowledge, direct responses, image analysis.

Choosing the Right Model

For Speed

When you need instant responses:

1. Gemini 2.0 Flash — Fastest overall
2. GPT-4o Mini — Very fast with good quality
3. DeepSeek V3 — Good balance

For Quality

When accuracy and nuance matter most:

1. GPT-4o — Best overall quality
2. DeepSeek R1 — Best reasoning
3. Gemini 1.5 Pro — Best for long documents

For Cost

When managing API costs:

1. DeepSeek V3 — Most cost-effective
2. GPT-4o Mini — Good value for OpenAI
3. Gemini 2.0 Flash — Competitive pricing

Model Configuration

Setting a Default Model

1. Open Options → AI Settings
2. Select your preferred default model
3. This model will be used for all actions unless overridden

Per-Action Models

Some actions might work better with specific models:

• Code explanations → DeepSeek (strong at coding)
• Creative writing → GPT-4o (best creativity)
• Quick fixes → Gemini Flash (fastest)

API Key Requirements

Each provider requires its own API key:

Provider	Get API Key
OpenAI	platform.openai.com
Google	aistudio.google.com
DeepSeek	platform.deepseek.com
xAI	console.x.ai

See API Keys Configuration for setup instructions.

Rate Limits & Usage

Each provider has different rate limits:

• OpenAI: Tier-based limits, starts at 60 RPM
• Google: Generous free tier, higher limits on paid
• DeepSeek: Very generous limits
• xAI: Moderate limits

Dialogix handles rate limiting gracefully and will retry failed requests.