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.
RELAI Free: $0. RELAI Enterprise: Custom pricing.
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
Capture signals from code, requirements, and production traces
Build and maintain EvalsWiki as versioned behavioral knowledge
Find missing eval coverage and unclear expectations
Generate complete evals with scenarios, environments, and evaluators
Optimize harness across prompts, tools, workflows, and code
Multi-objective optimization for quality, cost, latency, and KPIs
Model selection, migration, and routing with evaluation
Regression-controlled improvement with evaluation evidence
Versioned storage in repository with pull requests
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
Turns failures into replayable learning environments
Prevents regressions by keeping previous evals in the loop
Integrates with existing observability stacks and traces
Preserves business intelligence versioned in repository
Adapts harness to model changes without redefining use cases