Features
Single subscription for multiple open-weight coding models
2–5x higher rate limits than standard APIs
No API keys or provider accounts needed
Includes GLM 5.2, Kimi K2.7 Code, DeepSeek V4 Pro, Qwen3.7-Max, and more
Works inside Cline IDE, CLI, and Kanban
Flat monthly fee — no usage-based billing
Easy sign-up and cancellation
Supports Cline agentic workflows (planning, file editing, terminal commands)
Bring-your-own-key option still available for other providers
Laguna XS.2 model (33B params, 3B active, on-device)
Laguna M.1 model (225B params, 23B active, via API)
256K context length for multi-step reasoning
Multi-agent orchestration with planning and tool use
Sandboxed agent execution environments
Developer surfaces: agents, TUI, IDE extensions, binaries
Custom foundation models deployed on-prem or in VPC
Data connectors to repos, databases, data warehouses
Role-based access control for humans and agents
Executive-grade governance and auditability
On-prem, VPC, and workstation deployment (defense only)
Forward Deployed Research Engineers embed with teams
Real-time observability with end-to-end traces
Air-gapped network support
Open-weight model weights available
