Developer documentation
Everything you need to integrate the PrivateRouter API into your stack — quickstarts, billing internals, and operational guides.
Getting started
5-minute API quickstart with OpenAI SDK examples
/docs/getting-started
API quickstart
OpenAI-compatible /v1 endpoint usage
/docs/api-quickstart
Billing & Stripe
Plans, top-ups, webhooks
/docs/billing
Agent hosting
PureVPS cross-sell + product catalog
/docs/agent-hosting
Inference fleet ops
GPU nodes, LiteLLM config, benchmarks
/docs/inference
Observability
Prometheus, Grafana, structured logs, request IDs
/docs/observability
Auto-routing
privaterouter/auto: preferred model + timeout-triggered fallback
/docs/routing
Plugins
Response Healing, Pareto Router, and OpenRouter-parity extensions
/docs/plugins
Document Library
Persistent, encrypted RAG over your uploaded PDFs/DOCX/MD/TXT
/docs/document-library
Per-key analytics + spend alerts
Per-key usage charts, daily caps, email + webhook alerts
/docs/key-analytics
Public model leaderboard
How models actually perform — public, no auth, SEO-indexed
/docs/leaderboard
Embeddable chat widget
Drop PrivateRouter chat on your site with one script tag
/docs/widgets
Model playground
Compare up to 4 models side-by-side on the same prompt
/docs/playground
Token + cost estimator
Live token count + USD cost estimate for any prompt + model
/docs/token-estimate
Saved prompt library
Version and render reusable prompts with variables
/docs/prompts
Migrating to PrivateRouter
5-minute drop-in switch from OpenAI / Anthropic / OpenRouter
/docs/migrate
Bitcoin Payments
Top up credits with on-chain Bitcoin — unique amount per invoice, no third-party processor
/docs/btc-payments
Team Accounts
Multi-user workspaces with shared credits, RBAC, and invitations
/docs/teams
Context Window Limits
Dynamic per-model + per-plan context caps for predictable throughput and pricing
/docs/context-limits
Autoscaling & Vast.ai
Per-model capacity-watcher agents, Vast.ai provisioning, money safety rails
/docs/autoscaling