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.
Grant Free: $0/month with one project and monthly check-ins. Grant Pro: $49/month ($40/month billed yearly, 2 months free) with daily check-ins across five projects. Grant Studio: $149/month ($124/month billed yearly, 2 months free) with check-ins every six hours across fifteen projects.
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
AI-powered DevOps team with specialized agents for CI, costs, runtime, security and dependencies
Draft pull requests for supported dependency and compatibility fixes
Multi-channel access via Slack, dashboard, or MCP client
AWS cost tracking with forecasting and budget variance analysis
Security findings aggregation from GitHub and AWS Security Hub
World State monitoring for API changes and dependency updates
Decision tracking and follow-up management
Executive reporting and one-pagers on Studio and Enterprise
Agent security testing for prompt injection and AI risks
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
Complete AI DevOps team as a service, eliminating need to hire
Nothing merges or deploys without human approval and review
Specialized AI agents that each own specific operational domains
Evidence-based findings with citations from your actual sources
Works with your existing tools: GitHub, AWS, Slack, and your own AI providers
Since.dev