Free trial with free credits on signup. Pay As You Go: top up balance starting from $20, pay per token used. Enterprise: custom pricing with dedicated servers, custom models, unlimited RPM and TPM, full staff training and integration.
Free during beta. Self-hosted is free under Apache 2.0 license. Enterprise options available on request.
Key features
1000+ AI models access
AI Playground for testing
OpenAI and Anthropic compatible
Low latency
99.9% uptime SLA
24/7 support
MCP integration
Volume discounts
Data security
Single API key for all providers
Prompt versioning with named aliases and diffs
Server-side prompt templating with conditionals and loops
OpenAI-compatible AI gateway with automatic model fallbacks
Virtual keys, budgets and per-key rate limits
LLM tracing through the gateway or over OpenTelemetry
Versioned tool catalog for function calling
Offline experiments and online evaluation rules
Prompt optimization with candidate rewrites
Team-wide audit trail of every change
MCP server for Claude Code, Claude Desktop, Cursor
What makes it different
Save up to 80% compared to OpenAI
Unified API across 1000+ models from different providers
Infinite scalability with low latency
Simple integration with existing OpenAI/Anthropic setups
Model playground for testing before production
Change prompts without a deploy by moving production alias