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.
Free during beta: up to 1,000 responses per month
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
Customizable React form components
Spam filtering and response screening
Company enrichment for each response
Multi-step forms that save progress
Send to Slack, email, webhooks or Postgres
Response versioning
Read responses from terminal
Fit scoring for leads
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
Built for coding agents to set up and modify like code files
Open source npm package under MIT license
Forms live in your site's code, not separate tools
Mirio