LaunchRoundsSubmit Software

Portkey: Run LLM apps with gateway and observability

Portkey is a platform that combines an AI gateway, observability, guardrails, governance and prompt management for teams building generative AI applications.

What is Portkey?

Portkey is a production stack for teams building with large language models. Its AI Gateway offers a unified API to many models with fallbacks, load balancing, retries and caching, while the observability dashboard records logs, traces, feedback and metadata so teams can watch model behaviour and spend. The platform also covers guardrails, prompt management with versioning and a playground, and governance features such as role-based access control and budget limits. It is offered as a hosted service with a free Developer tier, a $49/month Production plan and custom Enterprise pricing that adds private cloud, VPC hosting and compliance options.

Focus areas: AI Gateway, Guardrails, Prompt Management.

Who is Portkey for?

  • AI and ML engineering teams shipping LLM features
  • Platform teams that need to govern model access across an organisation
  • Consultancies running separate AI workloads for multiple clients

How much does Portkey cost?

Portkey starts at $49/mo. Always check the vendor’s own pricing page before you buy.

PlanPriceWhat you get
DeveloperFree Forever10k recorded logs per month; 3 days log retention, 30 days metrics; 3 prompt templates; community support
Production$49/month100k recorded logs per month; $9 per additional 100k requests; 30 days log retention, 90 days metrics; unlimited prompt templates; RBAC
EnterpriseCustom Pricing10 Mn Plus recorded logs per month; custom retention; SSO; private cloud, VPC hosting; SOC2 Type 2, GDPR, HIPAA; dedicated onboarding

Is Portkey worth it?

Portkey suits teams that need one place to route, monitor and govern LLM traffic rather than stitching together separate tools

Where Portkey is strong

  • Unified API across many LLM providers with fallbacks, retries and load balancing
  • Observability with logs, traces, feedback, metadata and cost tracking
  • Prompt management, guardrails and governance in the same platform

Where it falls short

  • Pricing page does not list a self-hosted or open-source plan price
  • The free Developer plan is not intended for production workloads

How do you get started with Portkey?

  1. 01Create an account and get an API key from the Portkey dashboard
  2. 02Install the SDK and point your existing model calls at Portkey with a few lines of code
  3. 03Configure routing, caching, guardrails and prompt templates for your use case

Portkey: frequently asked questions

What does Portkey actually do?

It provides an AI gateway, observability, guardrails, governance and prompt management so teams can run generative AI applications in production.

How much does Portkey cost?

There is a free Developer plan, a Production plan at $49/month with 100k recorded logs and $9 per additional 100k requests, and custom Enterprise pricing.

How many models can I access through Portkey?

The site states that Portkey gives access to 1,600+ LLMs through a unified API.

Can I self-host Portkey?

The pricing page lists an open source option to host yourself and deploy locally, and Enterprise adds private cloud, VPC hosting and data isolation.

Portkey alternatives

The closest tools in our directory, matched on category, focus areas and audience.

Portkey compared with its alternatives
ToolBest forFree planStarting priceFocus areas
PortkeyTeams taking LLM apps to production with monitoring and controlYes$49/moAI Gateway, Guardrails, Prompt Management
OrqTeams governing many AI agents, models and tool callsUnknown—AI Gateway, Guardrails
APIParkTeams needing one open-source gateway for AI and API trafficUnknown—AI Gateway
TrueFoundryTeams centralizing LLM, MCP and agent traffic with governanceYes$25/moAI Gateway, Model Deployment
HigressTeams centralizing LLM, Agent and MCP traffic behind one gatewayUnknown—AI Gateway, MCP
Mistral AITeams needing controllable, self-hostable language modelsYes$14.99/mo—
Twelve LabsDevelopers and media teams searching and analyzing large video librariesYes——
LangfuseTeams tracing, evaluating and improving LLM apps in productionYes$29/moPrompt Management
Promptitude.ioTeams managing and deploying prompts across multiple AI modelsYes$39/moPrompt Management
LangtailTeams that need shared, testable prompt management for LLM appsYes$99/moPrompt Management
Upstage AITeams automating document parsing and extraction with LLM APIsNo$100/mo—