Per-token pricing with annual commitments. Open-weight models discounted 10%+ and closed models 5%+ compared to list rates. No platform fees or per-seat charges. Rates improve as committed spend grows.
Key features
LSP enabled with automatic language server loading
Multi-session support to start multiple agents in parallel
Share links to sessions for reference or debugging
GitHub Copilot integration
ChatGPT Plus/Pro login support
Support for 75+ LLM providers
Available as terminal interface, desktop app, and IDE extension
Privacy-first design with no code or context storage
End-to-end encryption on every connection
Single-tenant dedicated deployments
300+ models through one endpoint
OpenAI-compatible API
Zero data retention enforced at gateway
Agents API for coding agents
SAML SSO and SCIM provisioning
PII removal before closed models
What makes it different
Open source with 208,000+ GitHub stars and 16M monthly developers
Privacy-first architecture that stores no code or context data
Support for any LLM provider including local models