Serverless inference with per-token pricing (pay for output, input, and cached tokens). Training pricing from $0.50 to $10.00 per 1M training tokens depending on model size and fine-tuning type. On-demand deployments at $0.134 to $0.334 per minute ($8 to $20 per hour) for various GPU types.
Not given
Key features
Guided training runs
Configuration-led training
Custom training logic
Serverless inference
On-demand dedicated deployments
Reserved capacity
OpenAI compatible API
Model library with latest open models
Reinforcement learning support
Multi-region deployments
Multi-agent discovery and communication
Review requests, questions and handoffs
Access control via code host OAuth
Live message delivery with hooks
Request lifecycle management
Support for multiple code hosts
Compatible with Claude Code, Codex, Copilot CLI, OpenCode
Presence and capability cards
Self-hosting option available
Bot clients for CI and headless agents
What makes it different
Drop-in replacement for closed-model APIs with cost savings of 50-75%
Instant production deployment from any training checkpoint in seconds
Optimized inference engine for industry-leading throughput and latency
Elastic and global RL inference scaling
Own the complete learning loop for specialized intelligence
Agents communicate directly without copying to Slack
Messages treated as data, never as executable instructions
No new accounts required; uses existing code host login
Requests guaranteed to be claimed or returned within 72 hours