Portkey sits between your application and model providers, giving teams a common interface for provider access, routing, resilience, and observability. You can use its hosted service or operate an open-source gateway yourself; self-hosting offers more control over where the gateway runs, but makes your team responsible for its infrastructure and availability.
What Portkey does in an LLM application
Portkey describes itself as an AI gateway and production platform: an application sends requests through the gateway, which connects to supported model providers. The goal is to centralize parts of provider integration and request handling instead of implementing each provider connection and operational control separately. Portkey’s current company site also uses the name “PRISMA AIRS AI Gateway” in its enterprise positioning. Portkey
As an Amazon Associate I earn from qualifying purchases.
Quick wins for a faster PC:
Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Clear out junk files and repair common Windows errorsFree Scan →Scan for outdated or missing drivers - takes under a minuteDriver Scan →The gateway feature overview describes conditional routing, automatic fallbacks, retries, load balancing, timeouts, and caching. Its Gateway 2.0 announcement also describes circuit breakers and usage policies. These mechanisms can help respond to provider errors, distribute requests, and constrain usage; they do not guarantee provider uptime or make an application’s outputs correct. Which controls are available, and how they are configured, may depend on the release and plan. AI gateway features · Gateway 2.0 announcement
Choose a deployment model
| Option | What you operate | What to verify |
|---|---|---|
| Hosted Portkey | Portkey operates the gateway service, reducing the infrastructure your team must run. | Current plan price and limits, log retention, security controls, data residency, and the request and data paths for your configuration. Portkey pricing |
| Open-source, self-hosted gateway | Your team operates the gateway software and its supporting infrastructure, including availability and upgrades. | Supported deployment method, prerequisites, release-specific configuration, upgrade process, license, and which features are included in the version you select. Portkey documentation · Official gateway repository |
| Enterprise on-premises offering | A commercial deployment option for organizations seeking additional enterprise controls. | Exact feature entitlements, deployment architecture, support, and commercial terms with Portkey. Its Gateway 2.0 article lists SSO, SCIM, AWS KMS, RBAC, JWT, audit logs, and multi-workspace as enterprise on-prem capabilities; confirm current availability directly. Gateway 2.0 announcement |
Self-hosting changes where and how your team runs the gateway; it does not, by itself, establish that all data stays private or that every control is available without a commercial arrangement. Establish the actual control-plane and data paths, retention behavior, and edition terms for your design before choosing.
#1 Best Overall
- ONE-CLICK HA INSTALL - Deploy Home Assistant in seconds, no coding. Unifies multi-brand devices into one control center. Includes one-click HACS, Add-on Manager, OTA, backup, and 30s auto-restore watchdog. Full Linux SSH and Docker access.
- AI HOME AUTOMATION - OpenClaw AI agent learns your routines to auto-adjust lighting, climate, and devices. Skip YAML—describe needs in plain language and AI creates automation instantly. Proactively recommends useful automations, evolving into a smart household manager.
- MATTER BRIDGE - Connects Zigbee, Wi-Fi, and other smart devices into Apple Home, Alexa, and Google Home. Generates a Matter pairing QR code—simply scan with your preferred app to add devices. Control everything by voice via HomePod, Echo, or Nest for a unified multi-platform smart home.
- FULL AI SERVER - A compact 24/7 OpenClaw AI server beyond smart home control. Handles writing, research, emails, and content generation as your everyday AI assistant. Saves hardware costs and power versus a separate PC/Mac. Affordable, low-maintenance local AI.
- MOBILE APP SETUP - Download the free LinknLink App, sign in, and add multi-brand devices via smartphone. All device info auto-syncs to HomeClaw—no repeated config or manual importing. Drastically reduces setup time and effort for first-time installation and future expansion.
What the hosted tiers indicate—and what they do not
When Portkey’s pricing page was reviewed on October 4, 2026, it listed a free hosted tier for prototyping and evaluation, a Production tier at $49 per month, and custom-priced Enterprise. The page said the free tier was not suitable for production workloads. It also distinguished tiers by log limits, retention, and feature availability. Those prices and terms are time-sensitive, so consult the current pricing page rather than treating these figures as evergreen. Portkey pricing
The same page described the listed Production tier as not recommended for organizations requiring custom security controls or data-residency guarantees. Check the current wording and confirm whether a plan meets your specific requirements before sending production traffic.
PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchRank #2
- NO SUBSCRIPTION FEES & PRIVATE LORAWAN NETWORK: Build a local LoRaWAN IoT network with the built-in SIoT server and pre-installed Node-RED. Collect data, create dashboards, and run automation flows locally without required cloud service fees. Suitable for DIY makers, home gardeners, educators, and small IoT prototype projects.
- LOCAL DATA PROCESSING & PRIVACY CONTROL: Sensor data can be processed on the local network through the built‑in MQTT/SIoT server, reducing reliance on third‑party cloud platforms. Local automation rules continue running when internet access is unavailable — suitable for home, garden, greenhouse, and classroom IoT setups.
- 4KM COVERAGE & 8-CHANNEL RELIABILITY: Equipped with the SX1302 8-channel LoRaWAN chip, -140dBm sensitivity, 27dBm max transmit power, and included 5dBi antenna. Supports up to 4km coverage in open environments, helping connect garden sensors, greenhouse nodes, garages, mailboxes, and remote monitoring points.
- NODE-RED DRAG-AND-DROP VISUAL AUTOMATION：Automation rules, data dashboards, and control logic can be built with little to no coding using the pre‑installed Node‑RED. Flows such as reading soil moisture, checking temperature, and sending relay commands are created through a visual interface — reducing setup time for maker, education, and prototype projects.
- EASY SETUP WITH WIFI AP & MQTT INTEGRATION: Configure the gateway via Wi-Fi AP mode using a laptop or mobile device. Built-in MQTT broker supports integration with Node-RED dashboards, and other MQTT-compatible platforms. Designed for indoor residential, educational, and prototyping use; not intended for outdoor installation.
How routing and resilience fit together
Routing rules can direct requests according to configured conditions; fallbacks and retries can provide alternate handling when a request fails; load balancing can distribute work; and timeouts set limits on waiting for a response. Caching may avoid repeating some work, while circuit breakers, as described in the Gateway 2.0 article, can react to latency or error rates. The announcement also describes usage policies based on requests, tokens, or cost. AI gateway features · Gateway 2.0 announcement
These are operational building blocks, not automatic guarantees. Teams still need to choose routing conditions, set sensible limits, account for provider-specific behavior, and test how their application handles errors and fallback responses. Confirm the controls and syntax against documentation for the gateway version and plan being deployed.
Provider and local-model compatibility
Portkey names providers including OpenAI, Anthropic, Google Gemini, Cohere, Mistral, Hugging Face, AWS Bedrock, and Azure OpenAI. Its Universal API documentation describes a common OpenAI-style interface, and the docs also cover compatible local or privately hosted endpoints. Compatibility depends on the provider interface and endpoint exposed, as well as the modality and API features your application needs; a common request shape does not mean every provider implements every capability identically. Provider integrations · Universal API documentation
Portkey’s homepage provides Node/JavaScript and Python SDK examples. Use the current documentation for working initialization, provider configuration, and credential handling rather than copying a snippet without checking its version and security assumptions. Portkey homepage and SDK examples
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.A practical deployment checklist
- Map the request path. Decide which application calls will pass through Portkey, which providers or compatible endpoints they need, and whether any data must stay within a specified boundary.
- Select hosted, self-hosted, or enterprise on-prem. Compare operational responsibility with required security, residency, and governance controls; verify current plan and licensing terms.
- Pin down the release and deployment method. Follow the current official documentation and repository for supported prerequisites, configuration, and upgrade guidance. Do not assume deployment steps from one release apply to another. Documentation · Gateway repository
- Configure provider access and routing. Use the relevant provider integration and set only the routing, fallback, retry, timeout, cache, or usage controls supported by your selected version and edition.
- Test failure and policy behavior. Validate provider errors, fallback paths, latency limits, and applicable request, token, or cost policies in a controlled environment before production use.
- Review operational ownership. For self-hosting, assign responsibility for infrastructure, availability, upgrades, monitoring, and incident response. For hosted use, verify plan limits, retention, and security or residency fit.
Licensing and feature entitlements need version-specific checks
Portkey’s Gateway 2.0 article describes semantic caching, circuit breakers, budgets, a model catalog, metadata governance, and configuration management as capabilities in the open-source gateway it discusses. It presents the enterprise on-prem controls separately. A blog description or pricing page is not a substitute for the license text and feature entitlements governing a particular release. Before commercial use, redistribution, or relying on an edition-specific control, check the official repository’s license and confirm terms with Portkey. Gateway 2.0 announcement · Official gateway repository
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
