Twigg sells conversation state as a service, stored outside every model provider.

Twigg pitches a stateful LLM API that holds conversation history, fits the context window, routes across Anthropic, OpenAI, Google, xAI, Fireworks and OpenRouter, and tracks cost, so you can switch models mid-conversation without moving state. The argument is provider lock-in: conversations live at Twigg rather than at whichever lab you called last, which trades one lock-in for another but a cheaper one. No pricing published and no second source, so read it as a category signal.