Skip to content
Portkey

Self-hosted alternatives to Portkey

200 self-hosted apps like Portkey, closest match first.

Top picks

  1. G

    GoModel

    Launch

    AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative with observability, guardrails, streaming,

    FreeSelf-hosted

  2. O

    OmniKey-AI-Unified-Key-Manager

    Launch

    A self-hosted LLM proxy and failover gateway supporting OpenAI & Gemini compatible endpoints. Routes requests dynamically across 12+ LLM platforms with automatic fallback, key scheduling, rate-limit tracking and encrypted credential storage

    FreeSelf-hosted

  3. B

    BricksLLM

    Launch

    🔒 Enterprise-grade API gateway that helps you monitor and impose cost or rate limits per API key. Get fine-grained access control and monitoring per user, application, or environment. Supports OpenAI, Azure OpenAI, Anthropic, vLLM, and open

    FreeSelf-hosted

  4. T

    The OSS LLMOps Stack

    Launch

    Modular, open source LLMOps stack that separates concerns: LiteLLM unifies LLM APIs, manages routing and cost controls, and ensures high-availability, while Langfuse focuses on detailed observability, prompt versioning, and performance eval

    FreeSelf-hosted

  5. I

    Inference Gateway

    Launch

    An open-source, cloud-native, high-performance gateway unifying multiple LLM providers, from local solutions like Ollama to major cloud providers such as OpenAI, Groq, Cohere, Anthropic, Cloudflare and DeepSeek.

    FreeSelf-hosted

  6. O

    OpenGateLLM

    Launch

    OpenGateLLM is an open-source API gateway for generative AI. It is built for organizations that want full control over their data and infrastructure, and it is optimized for self-hosted models. The gateway centralizes, secures and governs a

    FreeSelf-hosted

More like Portkey

7
Y

YoloRouter

A self-hosted, OpenAI-compatible LLM gateway

Launch
8
L

Langfuse

Trace, evaluate, and improve AI agents with one open platform

Launch
9
R

Routerly.ai

Self-hosted LLM gateway that routes requests across AI providers

Launch
10
G

GPT Load

Self-hosted AI gateway for multi-channel, multi-credential setups

Launch
11
S

Spanlens

Drop-in observability platform for OpenAI, Anthropic, and Gemini

Launch
12
O

Octopus

One Hub All LLMs For You | 为个人打造的 LLM API 聚合网关

Launch
13
A

Agenta

Open-source LLMOps platform for prompt management, LLM evaluation

Launch
14
O

Otari

Open-source, OpenAI-compatible LLM gateway you run yourself

Launch
15
C

CliRelay

Self-hosted AI gateway for coding CLIs

Launch
16
V

VoidLLM

Privacy-first LLM proxy and AI gateway

Launch
17
L

Llamactl

Unified management and routing for llama.cpp, MLX and vLLM models

Launch
18
L

Latitude

AI Agent Observability & Monitoring

Launch
19
P

Paddler

Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs

Launch
20
O

ObsidianArc

A self-hosted AI platform with a Go server, multi-provider routing, usage…

Launch
21
P

Prismor

Self-hosted runtime control plane for AI agents

Launch
22
O

OS

Enables organizations to create and deploy customizable AI agents

Launch
23
O

Ollama

Load and run large LLMs locally to use in your terminal or build your apps

Launch
24
L

Llmaker

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Launch
25
L

LLMKube

Kubernetes operator for self-hosted LLM inference with pluggable runtimes

Launch
26
L

Lmnr

Laminar - open-source observability platform purpose-built for AI agents

Launch
27
A

Alma by Olivares.AI

Self-hosted control plane that maps and governs what your AI agents can reach

Launch
28
O

OrcaRouter-Lite

Self-hosted LLM router with a managed safety net

Launch
29
M

Muxi

Deploy intelligence. Open-source infrastructure for AI agents in production

Launch
30
M

Matrixhub

An Open-source, self-hosted AI model hub

Launch
31
L

Laminar

Laminar is an open-source platform

Launch
32
C

Cloudflare AI Web

Cloudflare AI Platform with one-click deployment

Launch
33
A

API7 cloud

Deploy and manage projects effortlessly

Launch
34
K

Keirouter

Your friendly, blazing-fast, self-hostable AI gateway

Launch
35
O

Orbit

Self-hosted AI gateway for private RAG, natural-language data access

Launch
36
A

Agentsystems

Self-hosted app store and runtime for AI agents

Launch
37
O

Open WebUI

Run AI on your own terms

Launch
38
C

ccLoad

Self-hosted AI API gateway for Claude Code

Launch
39
P

Proxify

An open-source, lightweight, and self-hosted reverse proxy gateway for AI APIs

Launch
40
V

Valmis

The AI Agent designed for work with security in mind

Launch
41
O

Olla

High-performance lightweight proxy and load balancer for LLM infrastructure

Launch
42
E

EpicStaff

Source-available, self-hosted platform for building AI agent flows

Launch
43
A

Aivory

Self-hosted AI chat platform with multi-step tool calls, persistent Python…

Launch
44
M

Mission Control

Self-hosted control plane for AI agents: dispatch tasks, review runs

Launch
45
L

LLM Harbor

Containerized LLM toolkit

Launch
46
G

GPTPortal

A feature-rich portal to chat with GPT-4, Claude, Gemini, Mistral, & OpenAI…

Launch
47
A

AgentsMesh

Self-hostable AI Agent Workforce Platform

Launch
48
M

MOVO

Turn DeepSeek Harness into a self-hosted enterprise Agent platform

Launch
49
O

Oriveo

Open-source, bring-your-own-key (BYOK) multi-model AI chat client for iOS…

Launch
50
A

AIClient2API

Self-hosted multi-protocol AI API proxy for Antigravity, Codex, Grok, Kiro

Launch

About Portkey

P

Portkey

Full-stack LLMOps platform to monitor, manage, and improve LLM-based apps

Portkey is a production platform for teams building apps on large language models. It combines an AI gateway, observability, guardrails, prompt management and governance in one product. The gateway gives a universal API to access more than 1,600 LLMs, with fallbacks, load balancing, retries and caching, and key management in one place. Observability records logs and traces for each request, with feedback, custom metadata, filters and alerts, so teams can monitor behavior and catch anomalies and usage spikes early. Prompt management provides templates, a playground, API endpoints, versioning and variables for prompts. Guardrails add deterministic checks and, on higher plans, LLM and partner guardrails. Team features include role-based access control and service account API keys. The site lists plans from a free developer tier for prototyping, to a production plan with more logs and longer retention, up to custom enterprise pricing. The site also notes that Portkey is now marketed as the PRISMA AIRS AI Gateway for enterprises.

Price
Freemium
Category
AI
Website
portkey.ai