Roadmap

UI visibility for prompt caching and local cache usage

Broader provider support, including Cohere, Command A, and Operational

Full support for the OpenAI /conversations lifecycle

Guardrails hardening: better UI, simpler architecture, easier custom guardrails, and response-side guardrails before output reaches the client

Provider-native passthrough for all providers, beyond the current beta coverage

Budget management with limits per user_path and/or API key

Editable model pricing for accurate cost tracking and budgeting

Full support for the OpenAI /responses lifecycle

Anthropic-compatible /messages ingress and /messages/count_tokens

Prompt cache visibility showing how much of each prompt was cached by the provider

Fix failover charts in the dashboard

Commercial features