Serverless inference with pay-per-use token pricing ($0.0015 to $4.50 per 1M tokens for chat/vision models). Provisioned throughput with reserved PTUs for committed capacity. Dedicated GPU endpoints at $5.49-$8.99 per hour. Fine-tuning from $0.34-$40 per 1M tokens. GPU clusters at $1.99-$9.99 per GP
Free: up to 5 agents, no card required. Starter: $49 USD per month for up to 25 agents. Pro: $199 USD per month for unlimited agents. Per-agent pricing with no charge per request or token.
Key features
GPU clusters at scale with autoscaling
Voice agent infrastructure with sub-second latency
Comprehensive model library with 25+ regions
Stable signed identity per agent tied to organization
Complete event record: runs, model calls, tool calls, errors, retries with timing
Events hashed, chained and signed before leaving host
Real-time fleet view with error rates and instance comparison