AI Providers
Connect to your preferred AI models to power your agent. Link directly to major providers like OpenAI, Google, and Anthropic, or use OpenRouter to access 100+ models through a single integration.
OpenAI
FreeIndustry leader in conversational AI technology
OpenAI's GPT models are the industry standard for conversational AI. From cost-effective GPT-4o Mini to powerful GPT-5 variants, find the perfect balance of speed, cost, and capability. Ideal for customer support, content creation, and complex reasoning.
Supported Models
GPT-5 Mini
GPT-5 Nano
GPT-4.1
GPT-4.1 Mini
GPT-4.1 Nano
GPT-4o
GPT-4o Mini
GPT-4 Turbo
GPT-4
Text Embedding 3 Small
Text Embedding 3 Large
Text Embedding ada 002
Answers accuracy
- ✅ 99%+ accuracy on standard benchmarks
- 🎯 Excellent at nuanced queries and context
- 🛡️ Helpful, harmless, and honest outputs
Speed
- ⚡ GPT-4o Mini: Near-instant responses (<500ms)
- 🚀 GPT-4o/GPT-5: Fast throughput for complex tasks
- ✨ Optimized for speed without quality loss
Cost Effectiveness
- 💰 GPT-4o Mini: Best value for high-volume use
- 📊 Scales efficiently for thousands of conversations
- 💎 Premium models offer competitive rates
Google Gemini
FreeGoogle's advanced multimodal AI powerhouse
Google Gemini leverages massive infrastructure and real-time search for up-to-date answers. Gemini 2.5 Flash delivers exceptional speed, while Gemini 2.5 Pro handles complex reasoning. Perfect for businesses needing Google integration and current information.
Supported Models
Gemini 2.5 Flash
Gemini 2.5 Flash Lite
Gemini 2.5 Pro
Gemini 2.0 Flash
Gemini Embedding 001
Answers accuracy
- ✅ 99%+ accuracy on standard benchmarks
- 🎯 Excellent at nuanced queries and context
- 🛡️ Helpful, harmless, and honest outputs
Speed
- ⚡ Gemini 2.5 Flash: One of the fastest models (<400ms)
- 🚀 Flash-Lite: Even faster for simple queries
- 💪 Pro maintains speed for complex reasoning
Cost Effectiveness
- 💰 Best cost-per-response in the industry
- 📊 Flash-Lite: Ideal for high-volume deployments
- 💎 Competitive pricing for thousands of conversations
Claude (Anthropic)
FreeSafety-focused AI with superior reasoning capabilities
Claude is designed with safety and reliability at its core. Known for exceptional reasoning, long-context understanding, and careful outputs. Ideal for complex analysis, document processing, and businesses prioritizing accuracy and safety.
Supported Models
Claude Sonnet 4.5
Claude Haiku 4.5
Claude Opus 4.5
Claude Opus 4.1
Claude Sonnet 4.0
Claude Opus 4.0
Claude 3 Haiku
Answers accuracy
- ✅ Opus 4.5: Leads in complex problem-solving
- 🎯 Sonnet 4.5: Excellent accuracy for business use
- 🛡️ All models: Helpful, honest, harmless
Speed
- ⚡ Haiku 4.5: Fast responses for simple queries
- 🚀 Sonnet/Opus 4.5: Excellent speed for complex reasoning
- ⚖️ Balanced thoroughness with response time
Cost Effectiveness
- 💰 Haiku 4.5: Excellent value for high-volume use
- 💎 Sonnet 4.5: Premium capabilities at reasonable cost
- 👑 Opus 4.5: Top-tier for best reasoning
DeepSeek
FreeCost-effective solution with exceptional coding abilities
DeepSeek Chat v3.2 offers industry-leading cost efficiency. Known for strong technical reasoning and coding capabilities, it delivers solid performance at a fraction of premium model costs. Perfect for technical support, troubleshooting, and code-related tasks.
Supported Models
DeepSeek Chat v3.2
Answers accuracy
- 💻 Excels at coding and technical reasoning
- 🔧 Reliable for technical support and troubleshooting
- 📊 Strong at structured information retrieval
Speed
- ⚡ Fast response times for real-time interactions
- 💨 Competitive speed for conversational tasks
- 🔧 Optimized for cost without sacrificing speed
Cost Effectiveness
- 💰 Best cost-per-response in the industry
- 📉 60-70% cheaper than premium models
- 🚀 Ideal for startups and budget-conscious businesses
Grok (xAI)
FreeFast and efficient AI models from xAI
Grok from xAI offers fast, efficient models with real-time information access. Known for up-to-date knowledge and a conversational style. The "Fast" variants prioritize speed while maintaining quality, ideal for high-volume, real-time conversations.
Supported Models
Grok 4.1 Fast (Reasoning)
Grok 4.1 Fast (Non Reasoning)
Grok 4 Fast (Reasoning)
Grok 4 Fast (Non Reasoning)
Grok 3 Mini
Grok 3 Mini Fast
Answers accuracy
- ✅ Real-time data access for up-to-date info
- 🎯 Grok 4.1 Fast (Reasoning): Superior for complex queries
- 💬 Engaging, conversational responses
Speed
- ⚡ Fast models: Near-instant responses (<350ms)
- 🚀 Non Reasoning: Fastest throughput available
- 💪 Reasoning variants balance speed with analysis
Cost Effectiveness
- 💰 Competitive pricing for Fast variants
- 📊 Grok 3 Mini Fast: Excellent value for high-volume
- 💎 Grok 4.1 Fast: Premium at reasonable rates
OpenRouter
FreeOne API for ~200 AI models across all providers
OpenRouter gives you one API key to access GPT-4o, Claude, Gemini, Mistral, Llama, and ~200 other models. Switch providers instantly without changing your integration. Ideal for cost optimization, model comparison, and fallback routing.
Supported Models (via OpenRouter)
GPT-4o
Claude 3.5 Sonnet
Gemini 2.0 Flash
Llama 3.1 70B
Mistral Large
DeepSeek V3
+ ~200 more
Model Quality
- ✅ Access top-tier models from all providers
- 🎯 Same quality as native APIs
- 🔀 Choose the best model for each use case
Speed
- ⚡ Speed depends on chosen model
- 🚀 Flash models: Near-instant via OpenRouter
- 🔄 Switch models anytime without code changes
Cost Effectiveness
- 💰 Compare pricing across ~200 models
- 📊 Optimize costs by switching models
- 💎 Pay-as-you-go, no locked contracts
Explore All Features
Discover the full range of capabilities including AI Providers, Live Agent, Customers Board, and more.
Ready to Get Started?
Download the free plugin or explore our pricing plans to unlock advanced features and take your customer support to the next level.