One OpenAI-compatible API for every model with adaptive routing, hosted agents, pipelines, and observability
One private API key for leading AI models, pay once with no subscription or usage caps
Stage
Startup
Not given
Founded
2025
Not given
Based in
IN
Not given
Pricing model
Not given
Paid
Pricing
Free: $1 free credits on signup (90 days), 50 requests and 500K tokens per day on free models. Starter: $14/month (30% off with PROMO code), includes $20 in monthly credits, 10 RPM burst 1.5x, 2 pipelines. Paid: $35/month (30% off), includes $50 in monthly credits, 20 RPM, 4 pipelines. Pro Plus: $70
Not given
Key features
Access to 100+ open-weight and frontier AI models behind one endpoint
OpenAI-compatible HTTP endpoint
Semantic caching to reduce latency and costs
Reproducible pipelines composing models, tools, and data
Per-request structured traces with latency and cost breakdown
Adaptive routing with latency-aware fallbacks
Model-agnostic RAG, web search, and PII redaction via single header
Works with existing OpenAI SDK without code changes
Switch models with /model command while keeping the same key
No usage caps or weekly limits
Token caching at 20 times lower price
Setup in minutes with one command
Works with Claude Code, OpenCode and custom API implementations
Private key not shared with others
Real-time balance visibility
12-month balance validity
Free shared key available for testing
What makes it different
One unified invoice and observability dashboard across all models, agents, and pipelines
Transparent prepaid credits with per-token rates published in your dashboard
Hosted agents with explicit CPU and memory caps and fail-closed credit gates
No synthetic data in dashboards; all metrics reflect actual user traffic
No model retraining on customer data
Community-supported independent service with optional donations
Token caching reduces repeated content costs by 20x