Presets
- OpenRouter with the base URL https://openrouter.ai/api/v1
- Groq with the base URL https://api.groq.com/openai/v1
- Together with the base URL https://api.together.xyz/v1
- Ollama cloud at https://ollama.com/v1, or your own public HTTPS URL
- vLLM and LM Studio: your public HTTPS URL behind authentication
- Custom: any OpenAI-compatible URL
Requirements
- Tool calling must work. For vLLM, start the server with auto tool choice and a tool-call parser. In LM Studio, use models with a tool chat template.
- A context window of at least 16,384 tokens.
- Up to three extra headers for access proxies.
Custom URLs are checked on every request: HTTPS only, public addresses only.