Strengths differ
Use one model for analysis and another for writing code — within the same conversation.
AI models
One conversation. Any model.
Use the provider that suits the task — and switch without starting over when a model reaches its limit.
Hit a limit? Keep going.
Usage limits, outages and new releases are part of working with AI. In MCPtoAI, your conversation is at the centre of your work — not the provider.
Choose another model from the model menu and carry on. The conversation history goes with you, so the new model can pick up where the previous one stopped.
Supported AI providers.
Use your own key for cloud providers, or run models on your own computer.
Cloud providers
- OpenAI
- Anthropic
- DeepSeek
- xAI (Grok)
- Moonshot (Kimi)
- Mistral AI
- Groq
- Cerebras
- Together AI
- Fireworks AI
- OpenRouter
- NVIDIA NIM
- Replicate
- EVREN
Local and custom
- Ollama
- LM Studio
- Any OpenAI-compatible server
Available models depend on your provider account. Capabilities such as tool use and image input vary from model to model.
Choose the right model for each step.
Cloud or local
Run sensitive work on a local model, and use cloud models when you need more capability.
Your keys, your billing
You use your own provider accounts. Usage is billed by the provider, under your account.
Questions about models
Do I lose context when I switch models?
No. The conversation history is passed to the model you select. Models have different context sizes, so a very long conversation may not fit every model.
Can I use local models?
Yes. MCPtoAI works with Ollama, LM Studio and other OpenAI-compatible servers running on your computer. Local models do not need an API key.
Who pays for model usage?
You do, directly to the provider. MCPtoAI uses the keys you add, so usage appears on your own provider account.
Stop starting over.
Keep your work in one conversation and use whichever model fits the moment.