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.
| Plan | Price | What you get |
|---|---|---|
| Developer | Free Forever | 10k recorded logs per month; 3 days log retention, 30 days metrics; 3 prompt templates; community support |
| Production | $49/month | 100k recorded logs per month; $9 per additional 100k requests; 30 days log retention, 90 days metrics; unlimited prompt templates; RBAC |
| Enterprise | Custom Pricing | 10 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?
- 01Create an account and get an API key from the Portkey dashboard
- 02Install the SDK and point your existing model calls at Portkey with a few lines of code
- 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.
| Tool | Best for | Free plan | Starting price | Focus areas |
|---|---|---|---|---|
| Portkey | Teams taking LLM apps to production with monitoring and control | Yes | $49/mo | AI Gateway, Guardrails, Prompt Management |
| Orq | Teams governing many AI agents, models and tool calls | Unknown | — | AI Gateway, Guardrails |
| APIPark | Teams needing one open-source gateway for AI and API traffic | Unknown | — | AI Gateway |
| TrueFoundry | Teams centralizing LLM, MCP and agent traffic with governance | Yes | $25/mo | AI Gateway, Model Deployment |
| Higress | Teams centralizing LLM, Agent and MCP traffic behind one gateway | Unknown | — | AI Gateway, MCP |
| Mistral AI | Teams needing controllable, self-hostable language models | Yes | $14.99/mo | — |
| Twelve Labs | Developers and media teams searching and analyzing large video libraries | Yes | — | — |
| Langfuse | Teams tracing, evaluating and improving LLM apps in production | Yes | $29/mo | Prompt Management |
| Promptitude.io | Teams managing and deploying prompts across multiple AI models | Yes | $39/mo | Prompt Management |
| Langtail | Teams that need shared, testable prompt management for LLM apps | Yes | $99/mo | Prompt Management |
| Upstage AI | Teams automating document parsing and extraction with LLM APIs | No | $100/mo | — |

