---
title: "Meta’s Spark Muse 1.1 is now available on Databricks, fully governed by Unity AI Gateway"
description: "Databricks announces support for Meta’s Muse Spark 1.1 through Model Provider Services (MPS) in Unity AI Gateway, addressing fragmented API keys, access controls, and usage visibility when organizations adopt new models. An MPS is a Unity Catalog securable that stores provider configuration and an encrypted API key, while callers use their Databricks credentials and the gateway attaches the key at request time. The post demonstrates registering Muse Spark through the OpenAI provider type with Meta’s API base URL and Responses API, then governing use with Unity Catalog privileges, model allowlists, policies, rate limits, usage metering, and inference tables. Requests are routed through the gateway, where access and guardrails are applied before reaching Meta; usage, spend, tokens, latency, status codes, and optionally full payloads are recorded for attribution and audit."
---

# Meta’s Spark Muse 1.1 is now available on Databricks, fully governed by Unity AI Gateway

[Databricks](https://yomu.fyi/company/databricks) · Pavithra Rao, Shaotong Li, Martin Grund, Kelly Albano · Jul 17, 2026

**Type:** Announcement

## Summary

Databricks announces support for Meta’s Muse Spark 1.1 through Model Provider Services (MPS) in Unity AI Gateway, addressing fragmented API keys, access controls, and usage visibility when organizations adopt new models. An MPS is a Unity Catalog securable that stores provider configuration and an encrypted API key, while callers use their Databricks credentials and the gateway attaches the key at request time. The post demonstrates registering Muse Spark through the OpenAI provider type with Meta’s API base URL and Responses API, then governing use with Unity Catalog privileges, model allowlists, policies, rate limits, usage metering, and inference tables. Requests are routed through the gateway, where access and guardrails are applied before reaching Meta; usage, spend, tokens, latency, status codes, and optionally full payloads are recorded for attribution and audit.

## Context

Organizations adopting newly released models can end up with duplicated API keys, fragmented access controls, and no centralized visibility into usage, spend, token attribution, prompts, or pre-request policy enforcement.

## Approach / What changed

Model Provider Services in Unity AI Gateway represent external providers as Unity Catalog securables. The gateway stores provider keys in encrypted Unity Catalog connections, authenticates callers with Databricks credentials, applies permissions, model allowlists, policies, rate limits, and guardrails, then routes requests and records usage.

## Takeaways

- Muse Spark 1.1 can be registered through the OpenAI provider type using https://api.meta.ai/v1 and the /openai/v1/responses API type.
- Unity Catalog permissions govern service use: callers need EXECUTE on the service plus USE CATALOG and USE SCHEMA on its parent.
- Unity AI Gateway records token counts, latency, status codes, and external-model spend; request tags and inference tables support attribution, audit, and payload logging.

**Tags:** [AI Gateway](https://yomu.fyi/topic/ai-gateway), [AI Governance](https://yomu.fyi/topic/ai-governance), [Observability](https://yomu.fyi/topic/observability), [Unity Catalog](https://yomu.fyi/topic/unity-catalog)

- Source: [Databricks](https://www.databricks.com/blog/metas-spark-muse-11-now-available-databricks-fully-governed-unity-ai-gateway)
- Source URL: https://www.databricks.com/blog/metas-spark-muse-11-now-available-databricks-fully-governed-unity-ai-gateway
- Ingested by Yomu: 2026-08-30T16:54:23.432Z

[Read original post](https://www.databricks.com/blog/metas-spark-muse-11-now-available-databricks-fully-governed-unity-ai-gateway)