This is a project that unifies the management of LLM APIs. It can call multiple backend services through a unified API interface, convert them to the OpenAI format uniformly, and support load balancing. Currently supported backend services include: OpenAI, Anthropic, DeepBricks, OpenRouter, Gemini, Vertex, etc.

modelmerge is a powerful library designed to simplify and unify the use of various large language models, including GPT-4/4t/4o, GPT-3.5, Claude3/3.5, Claude2, Gemini1.5 Pro/flash, DALL-E 3, DuckDuckGo(gpt-4o-mini, claude-3-haiku, Meta-Llama-3.1-70B, Mixtral-8x7B), and Groq.

TeleChat: 🤖️ an AI chat Telegram bot can Web Search Powered by GPT-3.5/4/4 Turbo/4o, DALL·E 3, Groq, Gemini 1.5 Pro/Flash and the official Claude2.1/3/3.5 API using Python on Zeabur, fly.io and Replit.