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
Memory system with self-managing advanced memory
Isolated per-tenant instances with version rollback
Portable context server with files, notes and links
Sub-document multi-modal hybrid search
Structured data extraction from PDFs, websites and images
Autonomous agents for knowledge base automation
99.9% uptime SLA
AES-256 encryption at rest and SSL in transit
TypeScript SDK and REST API
Model-agnostic and framework-agnostic
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
Cut token spend by up to 81% through persistent agent memory instead of full context window stuffing
State-of-the-art on two leading AI memory benchmarks
Full-stack data layer eliminating need for multiple services
Production-tested at scale powering Fabric platform
Self-improving memory that tracks relationships and resolves contradictions