changelog-images-fixed

changelog/2026/january.mdx

@@ -16,7 +16,7 @@
 | Area | Key Highlights |
 | :----------- | :------------- |
 | **Platform** | • MCP Gateway GA <br /> • Claude Code with any provider <br /> • Inline Image URLs Plugin <br /> • Usage and Rate Limit Policy Enhancements |
 | **Gateway** | • Responses API hooks <br /> • Unified Rerank API <br /> • Dynamic model pricing (air gapped) |
 | **Guardrails** | • Azure Shield Prompt and Protected Material <br /> • Sequential execution <br /> • CrowdStrike AIDR |
 | **Models & Providers** | • All providers via <code>/messages</code> <br /> • xAI Realtime Voice <br /> • Google Maps grounding <br /> • <code>/messages</code> endpoint with Bedrock |
 | **Community & Events** | • Agent Harnesses Salon: BLR (Sat 28 Feb) |
@@ -27,20 +27,20 @@
 
 <iframe width="560" height="315" src="https://www.youtube.com/embed/6HvCmiJyADA?si=JGxcRfWtcM9ubd35" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>
 
 - **Built-in support for every auth type** — Use OAuth 2.1, API keys, or bring your own auth with Okta, Entra, and more.
 - **Central MCP registry** — Add and manage internal and external MCP servers in one place.
 - **RBAC** — Decide exactly which teams and members can use specific MCP servers and tools.
 - **Full observability** — See every MCP tool call with full context, logs, and traces.
 
 [Read more about MCP Gateway](/product/mcp-gateway)
 
 ## How Fontys ICT built an internal AI platform
 
 Fontys ICT, a university of applied sciences in the Netherlands, ran a six-month pilot with ~300 users to build a governed, multi-provider AI platform. 
 
-<img src="/images/changelog/fontys-ict-architecture.png" alt="Fontys ICT three-layer architecture: Frontend (OpenWebUI), Gateway (Portkey), and External providers (Azure EU, Green PT, Anthropic)" style={{maxWidth: "50%", borderRadius: "8px", margin: "24px 0"}} />
+<img src="https://userimg-assets.customeriomail.com/images/client-env-144095/1767177250767_AI%20platform%20architecture_01KDSZHTBZADZ0CQNZMDNPMEJX.png" alt="Fontys ICT three-layer architecture: Frontend (OpenWebUI), Gateway (Portkey), and External providers (Azure EU, Green PT, Anthropic)" style={{maxWidth: "50%", borderRadius: "8px", margin: "24px 0"}} />
 
 They used Portkey's gateway architecture so they could control access, keep usage within EU infrastructure, enforce budgets, and give students and staff equitable access to AI without losing oversight. [Read the whitepaper](https://arxiv.org/html/2512.08978v1)
 
 ## Platform
 
@@ -56,7 +56,7 @@
 
 ### The best way to use AI apps and tools!
 
-<img src="/images/changelog/claude-code-testimonial-eric-walk.png" alt="Eric Walk, VP at Perficient, on using Portkey with Claude Code for monitoring model usage and cost" style={{maxWidth: "80%", borderRadius: "8px", margin: "24px 0"}} />
+<img src="https://userimg-assets.customeriomail.com/images/client-env-144095/1770297832978_Group%201000006860%20(1)_01KGPZJMZAPZ631H0ECG98PY4E.png" alt="Eric Walk, VP at Perficient, on using Portkey with Claude Code for monitoring model usage and cost" style={{maxWidth: "80%", borderRadius: "8px", margin: "24px 0"}} />
 
 ### Inline Image URLs Plugin
 
@@ -67,7 +67,7 @@
 You can now get more precise with budget and rate limit policies by defining them using:
 
 - `virtual_key`: Match by virtual key slug
 - `provider`: Match by provider (e.g., openai, anthropic)
 - `config`: Match by gateway config slug
 - `prompt`: Match by prompt template slug
 - `model`: Match by model with wildcard support (e.g., @openai/gpt-4o, @anthropic/*)
@@ -82,22 +82,22 @@
 You can now add input/output guardrails, custom webhooks, and other hooks to Responses API requests, so policy enforcement stays consistent across your inference traffic.
 
 
 ### Unified Rerank API
 
 We’ve added a unified `/rerank` endpoint so you can swap between supported reranking providers (Cohere, Jina, Voyage AI) without changing your application code.
 
 
 ## Guardrails
 
 ### Azure Shield Prompt
 
 Azure Shield Prompt helps you spot jailbreak and prompt injection attempts in requests by scanning both system prompts and user messages. You can authenticate with either an API key or Entra ID.
 
 [Add this guardrail](/integrations/guardrails/azure-guardrails#azure-shield-prompt)
 
 ### Azure Protected Material
 
-<img src="/images/changelog/azure-protected-material.png" alt="Azure Prompt Shield and Azure Protected material detection in guardrails" style={{maxWidth: "80%", borderRadius: "8px", margin: "24px 0"}} />
+<img src="https://userimg-assets.customeriomail.com/images/client-env-144095/1770297391284_azure-protected-material_01KGPZ55WPYT12P2AWDQ844WJ2.png" alt="Azure Prompt Shield and Azure Protected material detection in guardrails" style={{maxWidth: "80%", borderRadius: "8px", margin: "24px 0"}} />
 
 Azure Protected Material scans LLM outputs for known copyrighted or protected text, helping you stay compliant with intellectual property requirements.
 
@@ -111,7 +111,7 @@
 
 ### CrowdStrike AIDR
 
 We’ve teamed up with CrowdStrike so you can connect Portkey directly with CrowdStrike AI Detection and Response. Scan LLM inputs and outputs for threats or sensitive content, keep data safe, automate compliance, and move faster with enterprise-grade security.
 
 [Connect CrowdStrike AIDR](/product/guardrails)