Looking Beyond Microsoft Foundry?

Foundry gives you the models Azure hosts — after you create resources, deployments, and quotas. PassingRight gives you every major lab and cloud — including Azure itself — behind one open-source, OpenAI-compatible API. No provisioning required.

Cloud-NeutralFully Open SourceNo Deployments or QuotasAzure Built In
Start for Free
View Documentation
Compare platforms

Every model on Foundry — without the Azure ceremony

Compare PassingRight and Microsoft Foundry (formerly Azure AI Foundry) features side by side

Why choose PassingRight?

No cloud lock-in — Azure is one of 40+ providers behind a single OpenAI-compatible API
No deployments or quotas — call any model instantly, no provisioning or TPM planning
Fully open source — self-host the entire platform under AGPLv3
Keep your Azure setup — bring your Azure credentials and route through Foundry with 0% markup

PassingRight

OPEN-SOURCE & CLOUD-NEUTRAL

From $0

Self-host free forever

Microsoft Foundry

FORMERLY AZURE AI FOUNDRY

Usage-based

Requires an Azure subscription

Cloud-neutral

Use any provider on any cloud — or none at all

Azure only

Open source & self-hostable

Run the entire platform on your own infrastructure

AGPLv3

OpenAI-compatible API

One request format across every model

Varies by model

Setup required

What you need before your first request

Sign up, copy a key
Azure subscription, resource, deployments

Providers behind one API

Clouds, labs, and fast independent hosts

40+ providers
Azure-hosted catalog (10,000+ models)

Frontier model coverage

OpenAI, Anthropic, Google, xAI, and more

All major labs
OpenAI, Claude — no Gemini

Fast inference hosts

Groq, Cerebras, and other speed-focused providers

No deployment management

Call any model without provisioning it first

Deployments + TPM quotas

Automatic provider routing

Routes on live uptime, throughput, price, and latency

Model router (OpenAI, Claude, OSS)

Failover across providers

Transparent retry on a healthy provider — even another cloud

Response caching

Built-in caching for repeated requests

Redis, 10s–1yr TTL
Prompt caching (select models)

Route to Azure

Keep Azure OpenAI and Foundry models in the mix

Built-in providers
—

Bring your own keys

Use your own provider credentials

0% markup
N/A (Azure billing)

Transparent platform fee

Predictable, easy-to-reason-about pricing

5% or 0% (BYOK)
Provider rates + PTU reservations

Real-time cost analytics

Per-request cost, latency, and usage in one dashboard

Azure Monitor / Cost Management

Guardrails

Prompt injection, PII, jailbreak, and secret detection

Already on Azure? Keep it — and stop depending on it.

Azure OpenAI and Microsoft Foundry are built-in PassingRightproviders. Bring your Azure credentials and your traffic keeps flowing with 0% markup — while every request gains automatic failover to other providers, response caching, guardrails, and per-request cost analytics. When you need a model Foundry doesn't host, it's already behind the same API.

Start Free with PassingRightView Pricing Details

No credit card required • Self-host option available • Enterprise support included

FAQ

PassingRight vs Microsoft Foundry

Common questions about using PassingRight alongside or instead of Microsoft Foundry, formerly Azure AI Foundry.

Can't find an answer? Contact us

Yes. Microsoft renamed Azure AI Foundry to Microsoft Foundry at Ignite in November 2025, and the new name took effect in the January 2026 product terms. It is the same platform — Foundry resources, projects, deployments, and quota — with Anthropic's Claude models now generally available alongside OpenAI's, and a model router that can pick across OpenAI, Claude, and open-weight models. This page keeps its original URL so existing links and searches still land here.