Portkey
Free tierProduction stack for Gen AI builders — AI Gateway, Observability, Guardrails & more
Free tier available·Technical·Powered by Multi-provider (1,600+ LLMs supported via unified API)·API available·Open source
Key strengths
Unified API access to 1,600+ LLMs via a single AI GatewayReal-time LLM observability, logging, and anomaly detectionBuilt-in guardrails and AI governance controlsPrompt management without hard-coded promptsOpen-source core with plug-and-play 3-line integration
Free tier + paid plans · from $49 USD/mo
San Francisco, USA
Founded 2023
Self-hostable
Facts verified against portkey.ai on
Recent changes
- Plans updated: Free tier (10k logs/month, 3-day retention); Production at $49/month (100k logs/month, 30-day retention, +$9 per additional 100k requests); Enterprise at custom pricing (10M+ logs/month, custom retention, private cloud, SSO, HIPAA, etc.)
Get alerts when Portkey changes
Free. We'll email you when pricing, the free tier, API access or open-source status changes.
No ratings yet
Technical Use Cases
Portkey is purpose-built for AI/GenAI engineering teams deploying LLM-powered applications in production. Common technical use cases include:
- Multi-provider LLM routing — Use the unified API to implement fallback chains, load balancing, or A/B testing across 1,600+ models without rewriting application logic
- LLM observability pipelines — Stream request/response logs, token counts, latency metrics, and cost data into a centralized dashboard for debugging and performance tuning
- Prompt versioning and deployment — Manage prompt templates with version control, enabling safe iteration and rollback without code deploys
- Output validation and guardrails — Enforce deterministic or ML-based safety checks on LLM outputs before they are returned to end users
- Cost and rate governance — Apply RBAC policies, per-team budget caps, and rate limits to prevent runaway LLM spend in multi-team environments
- Caching layer — Implement semantic caching to serve repeated or near-duplicate queries from cache, reducing latency and API costs
- Secure agentic workflows — Use the MCP Gateway to give AI agents controlled, auditable access to external tools and services
- Compliant enterprise deployments — Deploy on private cloud with SOC2 Type 2, GDPR, and HIPAA controls for regulated industries
Alternatives
See all alternatives