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
Axe-core automated accessibility scans with violation counts and per-rule details
Page structure review including landmarks, headings and nested lists
Tab and focus order analysis with tabindex flag detection
Image and alt text inventory
WCAG 2.2 color contrast checking
Browser control for navigating dynamic content
Session-based auditing with action logging
Integration with Claude, opencode and other MCP clients
Local execution with no data transmission
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
Runs locally on your machine without requiring an account or API key
Works with any MCP client including Claude Desktop and opencode
Provides comprehensive accessibility auditing through axe-core integration
Includes explicit audit workflow guidance for consistent evaluation
Drives a real Chromium browser for accurate testing of dynamic content