Portkey

AI gateway with observability, routing, and guardrails

Portkey is an AI gateway and observability platform providing a unified API for 200+ LLM providers with intelligent routing, caching, rate limiting, and guardrails. Route requests across OpenAI, Anthropic, Google, and more with automatic failover, load balancing, and cost optimization. Features request logging, prompt management, evaluation tools, and real-time monitoring. The open-source gateway can be self-hosted; Portkey Cloud adds managed observability and team features.

Rate

Website

Is this your product? →

About Portkey

Portkey provides a unified API gateway sitting between applications and LLM providers. Route requests across 200+ models from OpenAI, Anthropic, Google, Azure, and others with a single API call.

Intelligent routing enables automatic failover when providers are down, load balancing across models, and cost-based routing that selects the cheapest capable model. Response caching reduces costs and latency for repeated queries.

Guardrails filter inputs and outputs for PII, toxicity, and custom rules. Request logging captures full request/response data for debugging. Prompt management and evaluation tools support iterative improvement.

The open-source gateway can be self-hosted for data sovereignty. Portkey Cloud adds managed observability, team collaboration, and enterprise features.

editorial evaluation

Read our Portkey review (Score: 85)

Detailed hands-on evaluation by the aicoolies editorial team

Read review →

Pricing & Platform Specs

Pricing Summary

Open-source AI gateway & observability control plane for 250+ LLMs (Apache-2.0, $0 self-host). Portkey Cloud offers Developer plan ($0/mo with 10k logs/mo), Production plan ($49/mo with 100k logs included + $9 per 100k overage for semantic cache & advanced alerts), and Enterprise plan with VPC deployment, 10M+ logs, custom SLAs, SOC 2 Type II, and HIPAA compliance.

full pricing breakdown →

Supported Platforms

API Gateway, Python SDK, JS SDK, Self-hosted

Explore categories, tags & use cases

Use Cases

Cost Optimization API Integration

Alternatives

All Portkey alternatives →

Tokscale

CLI token usage tracker for AI coding agents

Tokscale is a CLI tool that tracks token usage and costs across AI coding agents including Claude Code, Codex, OpenCode, Gemini CLI, Cursor, and more. Built with a native Rust core for high-performance processing, it provides detailed breakdowns of input, output, cache, and reasoning tokens with real-time pricing calculations via LiteLLM data. Features include interactive 2D/3D contribution graphs, web visualization dashboards, global leaderboards, and JSON export for cost analysis.

freeOpen Source

Weights & Biases

ML experiment tracking and model monitoring

Weights & Biases is an AI developer platform for experiment tracking, artifact and model lineage, model monitoring, and Weave-based LLM evaluation. It helps teams log runs, compare metrics, manage datasets and model artifacts, and collaborate through dashboards, reports, alerts, SSO/RBAC controls, and hosted or self-managed deployment options.

freemium

Discover more tools in this category

Related Tools

computed discovery: shared active categories

OpenLIT

OpenTelemetry-native observability for LLM applications with evals and GPU monitoring

OpenLIT is an open-source AI engineering platform that provides OpenTelemetry-native observability for LLM applications. It combines distributed tracing, evaluation, prompt management, a secrets vault, and GPU telemetry in a single self-hostable stack. With 50+ integrations across LLM providers and frameworks, it lets teams monitor AI applications using their existing observability backends like Grafana, Datadog, or Jaeger.

Open Source

Grafana

Open-source observability platform for metrics, logs, and traces visualization.

Grafana is the leading open-source platform for monitoring and observability visualization. It connects to virtually any data source — Prometheus, Elasticsearch, InfluxDB, PostgreSQL, CloudWatch, Datadog, and 150+ others — to create beautiful, interactive dashboards. Used by millions of users at companies like Bloomberg, JPMorgan, eBay, and PayPal. Grafana Cloud offers a fully managed experience with generous free tier. The CNCF ecosystem standard for metrics visualization.

freemiumOpen Source

Latitude

Sentry-style observability for AI agent conversations

Latitude is an agent observability platform for teams that need to inspect LLM traces, conversations, issues, and evaluation feedback in one workflow. Its public repo and docs position it as a Sentry-style monitor for AI agents, with semantic search, issue detection, annotations, MCP-assisted fixes, and cloud or self-hosted deployment paths for production debugging.

freemiumOpen SourceTelemetry

Judgeval

Open-source post-building layer for agents — tracing, evals, and online monitoring

Judgeval is the open-source post-building layer for AI agents from Judgment Labs, providing OpenTelemetry-based tracing, hosted and custom evaluation scorers, and online behavior monitoring for LLM-powered applications. Instrument any function with a single decorator, score live production traffic against faithfulness and instruction-adherence checks, and feed real-world failures back into reinforcement learning or supervised fine-tuning loops.

Open Source

Sentrial

Production monitoring platform for AI agent reliability

Sentrial is a YC W26-backed monitoring platform for AI agent reliability in production. It semantically detects loops, hallucinations, tool misuse, and user frustration in real-time, then diagnoses root causes and recommends fixes. The platform claims 70% MTTR reduction via automated remediation including rollback, model retraining triggers, and webhooks. Sentrial positions itself as the Datadog for teams deploying autonomous AI agents at scale.

paid

Datadog

Cloud-scale monitoring, security, and analytics platform for modern infrastructure.

Datadog is a cloud observability and security platform that unifies metrics, traces, logs, RUM, synthetics, APM, and security signals. Current pricing pages list 1,000+ integrations for Infrastructure Monitoring, with Pro from $15/host/month and Enterprise from $23/host/month when billed annually.

freemium

Side-by-Side Comparisons

Portkey

Helicone

Portkey vs Helicone: AI Gateway Control Plane or Lightweight LLM Observability?

Portkey is the stronger fit for governed AI gateway control-plane needs, while Helicone is better when a team wants lightweight LLM observability, request analytics, caching visibility, and a simpler gateway path.

PortkeyHelicone

Langfuse

Portkey

Langfuse vs Portkey — Open-Source LLM Observability vs AI Gateway and Routing Platform

Langfuse and Portkey address different layers of LLM operations. Langfuse is an open-source observability platform for tracing, evaluation, and prompt management of LLM applications. Portkey is an AI gateway that routes requests across 200+ providers with caching, fallbacks, load balancing, and cost tracking, adding monitoring on top of its core routing functionality.

LangfusePortkey

Community experience

Sources & verification

Portkey Official Documentation & Repository

Sources checked: September 5, 2026
Content verified: September 6, 2026

Verification dates are editorial checks. Routine CMS saves and automatic updatedAt timestamps do not advance them.

FAQ

What is Portkey?

Is Portkey free?

Portkey offers a free tier alongside paid plans. Open-source AI gateway & observability control plane for 250+ LLMs (Apache-2.0, $0 self-host). Portkey Cloud offers Developer plan ($0/mo with 10k logs/mo), Production plan ($49/mo with 100k logs included + $9 per 100k overage for semantic cache & advanced alerts), and Enterprise plan with VPC deployment, 10M+ logs, custom SLAs, SOC 2 Type II, and HIPAA compliance.

Is Portkey open source?

Yes — Portkey is open source.

Is Portkey still maintained?

Yes — Portkey is active. Its listing was last verified on September 6, 2026.

What are the best Portkey alternatives?

The first editor-selected Portkey alternatives are Tokscale, Weights & Biases.

How does Portkey score in our review?

The published editorial review lists Portkey at 85/100 overall across speed, privacy, and developer experience. Check the review's evidence status and test metadata for its verification level.

Portkey

About Portkey

Read our Portkey review (Score: 85)

Pricing & Platform Specs

Pricing Summary

Supported Platforms

Categories

Tags

Use Cases

Alternatives

Tokscale