LLM observability & evaluation · Portkey

Portkey

AI gateway that routes and load-balances LLM calls across providers while logging traces, prompts, and feedback for observability.

Visit Portkey Alternatives

Portkey is primarily an AI gateway: a unified API in front of multiple LLM providers that adds retries, timeouts, fallbacks, load balancing, and guardrails to production LLM traffic, with observability as a built-in side effect of proxying every call. Every request routed through Portkey is logged with traces, feedback, and custom metadata, and prompt templates can be versioned and managed centrally, which makes it closer to a combined gateway-plus-observability tool than a pure tracing product. An open-source, self-hosted version covers the core gateway and basic dashboard for free. The hosted Developer plan is free for low volume but explicitly not meant for production; Production and Enterprise plans add higher log volumes, longer retention, RBAC, and private/VPC deployment.

At a glance

Vendor Portkey
Pricing model Free tier + paid plans
Free tier Yes
Deployment Cloud, Self-hosted
Open source Yes
Best for Teams that need a production LLM gateway (routing, fallbacks, guardrails) with logging built in, not just a tracing add-on.

Pricing

Open-source self-hosted gateway is free; hosted Developer tier is free but capped and not for production; Production is a monthly subscription with log-volume overage; Enterprise is custom with private/VPC deployment.

Plan Price Notes
Open source (self-hosted) Free Universal API, retries/timeouts, routing, guardrails, load balancing, basic dashboard
Developer Free forever 10k recorded logs/month, 3-day log retention, 30-day metrics retention; not for production
Production $49/month 100k recorded logs/month, $9 per additional 100k requests, 30-day log retention, RBAC, unlimited prompt templates
Enterprise Custom 10M+ recorded logs/month, custom retention, SSO, private cloud/VPC deployment, SOC 2/GDPR/HIPAA

Prices read from the vendor's own page on September 21, 2026. Vendors change prices; check the source before you budget.

Features

  • Unified API gateway across multiple LLM providers
  • Automatic retries, fallbacks, and load balancing
  • Request/response logging with traces and custom metadata
  • Prompt template management and versioning
  • Guardrails for content and policy enforcement
  • Open-source, self-hostable gateway core

Integrations

Profile last reviewed September 21, 2026

Head to head

Alternatives

Helicone Open-source LLM observability platform that logs and analyzes requests via a proxy or async SDK, with a free-tier hosted cloud. Langfuse Open-source LLM tracing and evaluation platform, available self-hosted for free or as a metered hosted cloud service. Lunary GDPR-focused LLM observability platform for tracing, prompt management, and human review, hosted in Europe or self-hosted.

Portkey in the index now

Terms to know

Data observability Continuous automated monitoring of pipelines and datasets to catch freshness, volume and quality problems early. Machine learning Building models that learn patterns from data to make predictions or decisions, rather than following hand-coded rules. LLM observability Monitoring a language model's live behavior in production, tracking its inputs, outputs, latency, cost, and failure patterns. Role-based access control (RBAC) Granting data or system permissions based on a user's assigned role rather than configuring access for each person individually.

Related guides

How to choose an LLM observability tool Pick an LLM tool by whether you need tracing, scoring or a gateway first — most teams eventually need all three, rarely from one vendor.