AI phone agents with integrated audio understanding, model routing, and voice optimization
Coding agents on cloud machines with a record of every session
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Paid
Free trial
Pricing
Cost-plus pricing: customers pay vendor list prices for models and voice plus hosting (15% of vendor costs, 0.5¢ to 2¢ per minute) plus company margin (17-25%). Lean calls cost from 2.0¢/min (1.18¢ vendors + 0.50¢ hosting + 0.35¢ margin). Receptionist calls cost 4.7¢/min (3.36¢ vendors + 0.50¢ hosti
Free trial: two machines, up to 2 vCPU and 4 GiB. Cuna Inference pricing: models available at varying rates, such as GLM-5.2 at $1.00 per million input tokens and $4.00 per million output tokens.
Key features
Multi-model architecture running multiple transcription and language models per call
Zeus AI agent that builds, tests and tunes voice agents automatically
Simulated call testing before live deployment
Live call monitoring and observability
A/B testing and automated fix suggestions
Integration wizard for CRM, VoIP and business software
Client portals for managing multiple agents
Knowledge base integration for agent grounding
Outbound campaigns with CSV upload and scheduling
Isolated session execution with bounded authority
Web console for machine management
Complete action recording and visibility
OpenAI-compatible Chat Completions API
OpenCuna terminal agent
Multiple model provider support
Cuna Memory for agent state persistence
Token-based pay-as-you-go pricing
What makes it different
Cost-plus pricing with no margin markup pass-through when vendor prices drop
Fully agentic Zeus AI that handles entire lifecycle from creation to optimization
Multi-model architecture for superior audio understanding vs 3-step pipelines
Starts at 2¢/min, cheaper than competitors and call center labor
Your Agent. Not a Vendor's.
The work ends. The proof remains.
Complete session records and operational transparency