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

ModelBest for
GPT-4oBest overall quality, multimodal
GPT-4o-miniFast, cost-effective everyday tasks
GPT-4-TurboLong context (128K tokens)
o1Complex reasoning and analysis
o3-miniFast reasoning at lower cost

Setup

  1. Get your API key from platform.openai.com/api-keys
  2. 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

ModelBest for
Claude 3.5 SonnetBest balance of speed and intelligence
Claude 3.5 HaikuFastest, great for simple Q&A
Claude 3 OpusMost capable, complex analysis

Setup

  1. Get your API key from console.anthropic.com
  2. 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

ModelBest for
Gemini 1.5 ProLong documents, complex tasks
Gemini 1.5 FlashFast responses, cost-effective
Gemini 2.0 FlashLatest generation, improved quality

Setup

  1. Get your API key from aistudio.google.com/apikey
  2. Enter the key when creating your chatbot and select Google as the provider

Choosing the Right Provider

NeedRecommended
Best overall qualityOpenAI GPT-4o
Fastest responsesGoogle Gemini 2.0 Flash
Lowest costOpenAI GPT-4o-mini or Claude 3.5 Haiku
Longest contextGoogle Gemini 1.5 Pro (1M tokens)
Complex reasoningOpenAI o1 or Claude 3 Opus
Persistent memoryOpenAI (Assistants API with threads)

All providers support streaming, markdown formatting, and code highlighting in the chat window.