---
schema_version: "1"
id: 01202f51fe02bececa43dd3830f18352907226f2e1864b19fcf3033342a3a421
title: Model Proxy Release Notes
collection: mulesoft
version: current
locale: en-us
portal_url: https://docs.salesforce.com/mulesoft/current/en-us/release-notes/gateway/model-proxy-release-notes.md
canonical_url: https://docs.mulesoft.com/release-notes/gateway/model-proxy-release-notes
source_site: docs.mulesoft.com
content_type: documentation
content_hash: 082659424431aedf59c1a55cae11c88db6190c5a0931d7237af57402c20e2771
description: MuleSoft Documentation Site
latest: true
---
---
product: Release Notes
version: master
---

# Model Proxy Release Notes

> For the full documentation index, see: https://docs.mulesoft.com/llms.txt

These release notes reflect enhancements, changes, and bug fixes for model proxy.

In addition to these release notes, see:

- [Omni Gateway Release Notes](https://docs.mulesoft.com/release-notes/gateway/gateway-release-notes)

## August 31, 2026

### What’s New

- Model proxy now supports semantic caching, which stores and reuses LLM responses based on semantic
  similarity to reduce latency and cost. Semantic caching supports Azure AI Search as the vector
  database.

  See [Semantic Caching](https://docs.mulesoft.com/general/model-proxy#semantic-caching) and
  [Configuring Semantic Caching Services](https://docs.mulesoft.com/general/model-proxy-semantic-caching-service).

- You can now secure model proxy connections with TLS by configuring a TLS context on the proxy
  consumer endpoint and on connections to provider endpoints.

  See [Create a Model Proxy](https://docs.mulesoft.com/general/model-proxy-create-model-proxy#create-a-model-proxy).

- Model proxy can now authenticate to LLM providers by using a secret stored in an external vault
  (AWS Secrets Manager, Microsoft Azure Key Vault, or HashiCorp Vault).

  See [Create a Model Proxy](https://docs.mulesoft.com/general/model-proxy-create-model-proxy#create-a-model-proxy).

- The Model Proxy Request Compression policy is now available for model proxies.

  See
  [Model Proxy Request Compression Policy](https://docs.mulesoft.com/gateway/latest/policies-included-llm-proxy-request-compression)
  and [Model Proxy Request Compression](https://docs.mulesoft.com/release-notes/gateway/policies/llm-proxy-request-compression-release-notes).

## August 6, 2026

### What’s New

- LLM Proxy is now renamed to model proxy.

- Model proxy now supports the Anthropic API format and native Anthropic models.

  See [Supported LLM Providers](https://docs.mulesoft.com/general/model-proxy#supported-llm-providers).

## May 9, 2026

### What’s New

- Model proxy now supports Advanced Scale semantic services that use vector databases to store up to
  2000 utterance vectors per prompt topic.

  See
  [Configure an Advanced Scale Semantic Service](https://docs.mulesoft.com/general/model-proxy-semantic-service#configure-an-advanced-scale-semantic-service).

- Agent Network now supports model proxies as Agent Broker LLM providers.

  See
  [Broker Project File References](https://docs.mulesoft.com/agent-network/latest/af-project-files#llmproviders-section).

- Model proxy can now dynamically extract API Keys (such as OAuth 2.0 tokens) from incoming requests
  to support dynamic LLM provider authentication.

- Model proxies now support NVIDIA Nemotron models.

  See [Supported Models](https://docs.mulesoft.com/general/model-proxy#brokers-section)

- Anypoint Monitoring now provides new dashboards for cost management.

## March 30, 2026

### What’s New

Model proxy provides a unified access layer for multiple Large Language Model (LLM) providers. Model
proxies are deployed to Omni Gateway to enable governance, intelligent routing, and cost management
for AI applications.

To learn more, see [Creating and Managing Model Proxies](https://docs.mulesoft.com/general/model-proxy).

## See Also

- [Known Issues](https://help.salesforce.com/s/issues)