AI Providers - OpenAI, Anthropic, Google
Configure multi-provider AI models for your BotByte chatbot.
Multi-Provider AI
BotByte supports three AI providers, each with distinct strengths. Choose the best model for your use case when creating a chatbot.
OpenAI (GPT)
BotByte uses the OpenAI Assistants API for GPT models. This provides:
- Persistent threads - Conversations maintain context across messages automatically
- Native function calling - The assistant can invoke tools defined in your chatbot settings
- Streaming responses - Text appears word-by-word for a responsive experience
Supported Models
| Model | Best for |
|---|---|
| GPT-4o | Best overall quality, multimodal |
| GPT-4o-mini | Fast, cost-effective everyday tasks |
| GPT-4-Turbo | Long context (128K tokens) |
| o1 | Complex reasoning and analysis |
| o3-mini | Fast reasoning at lower cost |
Setup
- Get your API key from platform.openai.com/api-keys
- You need at least Tier 1 for GPT-4 access. Check your tier at platform.openai.com/account/limits
Anthropic (Claude)
Claude models excel at long-form content, nuanced instructions, and careful reasoning.
Supported Models
| Model | Best for |
|---|---|
| Claude 3.5 Sonnet | Best balance of speed and intelligence |
| Claude 3.5 Haiku | Fastest, great for simple Q&A |
| Claude 3 Opus | Most capable, complex analysis |
Setup
- Get your API key from console.anthropic.com
- Enter the key when creating your chatbot and select Anthropic as the provider
Google (Gemini)
Gemini models offer strong multimodal capabilities and large context windows.
Supported Models
| Model | Best for |
|---|---|
| Gemini 1.5 Pro | Long documents, complex tasks |
| Gemini 1.5 Flash | Fast responses, cost-effective |
| Gemini 2.0 Flash | Latest generation, improved quality |
Setup
- Get your API key from aistudio.google.com/apikey
- Enter the key when creating your chatbot and select Google as the provider
Choosing the Right Provider
| Need | Recommended |
|---|---|
| Best overall quality | OpenAI GPT-4o |
| Fastest responses | Google Gemini 2.0 Flash |
| Lowest cost | OpenAI GPT-4o-mini or Claude 3.5 Haiku |
| Longest context | Google Gemini 1.5 Pro (1M tokens) |
| Complex reasoning | OpenAI o1 or Claude 3 Opus |
| Persistent memory | OpenAI (Assistants API with threads) |
All providers support streaming, markdown formatting, and code highlighting in the chat window.