{"slug": "metas-spark-muse-1-1-is-now-available-on-databricks-fully-governed-by-unity-ai", "title": "Meta’s Spark Muse 1.1 is now available on Databricks, fully governed by Unity AI Gateway", "summary": "Meta's Muse Spark 1.1 is now available on Databricks through Unity AI Gateway, enabling organizations to govern access, usage, and costs centrally via Unity Catalog. The integration allows teams to register the model once, apply Unity Catalog permissions, and track every request with token usage, latency, and cost attribution, eliminating API key sprawl and fragmented governance.", "body_md": "Unity AI Gateway provides access to any model, including Meta’s new Muse Spark 1.1, with unified data and AI governance, access and spend controls, and end-to-end observability, via Unity Catalog\n\nby [Pavithra Rao](/blog/author/pavithra-rao), [Shaotong Li](/blog/author/shaotong-li), [Martin Grund](/blog/author/martin-grund) and [Kelly Albano](/blog/author/kelly-albano)\n\n• Get day-one access to Meta's new Muse Spark 1.1 (and any model) through Model Provider Services in Unity AI Gateway. Register providers once in Unity Catalog to eliminate API key sprawl and centralize access across every team.\n\n• Teams can use familiar Unity Catalog permissions, rate limits, and guardrails to securely enable new models on day one, while keeping provider credentials encrypted and centrally managed.\n\n• Every request is automatically tracked with token usage, latency, cost attribution, and audit logs, giving platform teams end-to-end observability and enabling governance, budgeting, and compliance across all model providers\n\nEvery new model release promises better reasoning, lower costs, or new capabilities, and developers want access on day one. But every provider also introduces another set of API keys, another integration, and another governance surface for platform teams to manage. Without a centralized way to govern all model providers, access becomes fragmented, API keys proliferate, and visibility into usage and spend disappears.\n\n**Today, we're announcing support for ****Meta's new Muse Spark 1.1**** on Databricks through the new Model Provider Services (MPS) in Unity AI Gateway. MPS lets you connect and govern model providers, including OpenAI, Anthropic, Amazon Bedrock, and newly released models like Muse Spark 1.1, through Unity Catalog. **Now you can register models once, control access using familiar Unity Catalog permissions, and let every team query through Unity AI Gateway with full governance and observability in place.\n\nIn this post, we'll use Muse Spark 1.1 to show how organizations can adopt a newly released model on day one without compromising governance or security.\n\nSay your team wants [Muse Spark 1.1](https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/) the day it ships. One team creates a provider account and starts building with it. Another team requests its own API key. Soon, multiple copies of the same key are spread across notebooks, applications, and CI/CD pipelines, each managed independently. Access control is just as fragmented because there’s no consistent way to say “these three teams can use the premium model, everyone else uses the standard one.”\n\nOn the platform admin side, there is no unified view of spend, no token-level attribution, no record of which prompts left the building, and no place to enforce a rule before a request reaches a model provider. When finance asks why the Meta bill tripled, you can see the total in Meta's console, but not which team or workspace drove it in a single centralized report.\n\nThis pattern doesn't just apply to Muse Spark, as it is the same challenge organizations face every time they adopt a new model.\n\nA Model Provider Service is a governed Unity Catalog securable that represents an external provider. It lives in a catalog and schema, and holds the provider's connection configuration and API key. Callers reference the service by name and authenticate with their own Databricks credentials; the gateway attaches the provider's API key at request time. The API key is stored via a Unity Catalog connection, encrypted with a platform-managed or customer-managed key, and **never exposed directly to client consumers**.\n\nOnce a model provider service is registered in Unity Catalog, your organization gets three things: Choice, Control, and Clarity.\n\n*Figure 1. Register a provider once in Unity Catalog; every team and provider is governed through one gateway.*\n\nLet’s register the externally hosted Muse Spark 1.1 model as a Model Provider Service, lock down who can use it, turn on monitoring, and query it end-to-end.\n\n**Register the provider**\n\nIn order to use Muse Spark 1.1 on Databricks, you need to first register it in Unity Catalog. Obtain your Muse Spark API key from Meta's Model API, which is currently in Public Preview. Because Muse Spark is compatible with the OpenAI Responses API, you can register it using the OpenAI provider type to connect directly to Meta's API.\n\nRegister it in the Unity Catalog UI: **Catalog Explorer → Create → Create a service → Model provider service**, choose OpenAI, paste the Meta key as the **API key**, https://api.meta.ai/v1 as the **Base URL**, add muse-spark-1.1 as the model and set the model’s API type to /openai/v1/responses.\n\nWith the provider registered, two key security controls are applied. First, the API key is stored encrypted within the Unity Catalog. Second, the model list strictly defines which models and API surfaces are exposed, so any request for an unlisted model is intercepted and rejected at the gateway before it reaches Meta.\n\nThe service is a Unity Catalog securable, so you govern it using the same principles you apply to any other object. To query it, a caller needs EXECUTE on the service plus USE CATALOG and USE SCHEMA on its parent. The service creator or admins with MANAGE permission on the service can grant such privileges.\n\nTo grant access:\n\n*Figure 2. A single request: the gateway checks access, applies rate limits and policies, routes to Muse Spark, and logs usage.*\n\nBecause Muse Spark speaks the OpenAI Responses API, point any OpenAI-compatible client at the gateway and set one header for querying:\n\nThe additional header allows Unity AI Gateway to identify the model provider service and validate the caller's privileges. Once the privileges are validated, the gateway will resolve the configuration and route the request to the external model.\n\nUnity AI Gateway [meters](https://docs.databricks.com/aws/en/ai-gateway/usage-tracking) every request routed through the service. Every usage is reported in system.ai_gateway.usage with input/output token counts, latency, and status codes. Spend info is recorded in system.ai_gateway.external_model_spend. Add a [Databricks-Ai-Gateway-Request-Tags](https://docs.databricks.com/aws/en/ai-gateway/usage-tracking#tag-requests-for-usage-tracking) header to slice spend by project, and attach inference tables to log full request and response payloads to a governed Delta table for audit.\n\nAttach a [policy](https://docs.databricks.com/aws/en/data-governance/unity-catalog/service-policies/) to the service to enforce guardrails for each request, including default guardrails for common risks such as PII, prompt injection, and unsafe content, and the ability to add custom policies for your own rules. Guardrails run centrally at the gateway, so any unsafe prompt is caught before it reaches Muse Spark, no matter who sent it. Per-service **rate limits** cap capacity and cost.\n\nModel Provider Services are available across **AWS, Azure, and GCP**. Account administrators can enable the preview on the account console's **Previews** page.\n\nTo go deeper, see the docs on [Model Provider Services](https://docs.databricks.com/aws/en/ai-gateway/model-provider-services), [governing access](https://docs.databricks.com/aws/en/ai-gateway/govern-model-provider-services), and [querying through the gateway](https://docs.databricks.com/aws/en/ai-gateway/query-model-provider-services).\n\nUnity AI Gateway brings choice, control, and clarity so your team can use any model they want to. Enable the preview and try out Model Provider Services today!\n\nSubscribe to our blog and get the latest posts delivered to your inbox.", "url": "https://wpnews.pro/news/metas-spark-muse-1-1-is-now-available-on-databricks-fully-governed-by-unity-ai", "canonical_source": "https://www.databricks.com/blog/metas-spark-muse-11-now-available-databricks-fully-governed-unity-ai-gateway", "published_at": "2026-07-17 13:08:01+00:00", "updated_at": "2026-07-17 19:55:06.308305+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-products", "ai-infrastructure", "large-language-models"], "entities": ["Meta", "Databricks", "Unity AI Gateway", "Unity Catalog", "Muse Spark 1.1", "OpenAI", "Anthropic", "Amazon Bedrock"], "alternates": {"html": "https://wpnews.pro/news/metas-spark-muse-1-1-is-now-available-on-databricks-fully-governed-by-unity-ai", "markdown": "https://wpnews.pro/news/metas-spark-muse-1-1-is-now-available-on-databricks-fully-governed-by-unity-ai.md", "text": "https://wpnews.pro/news/metas-spark-muse-1-1-is-now-available-on-databricks-fully-governed-by-unity-ai.txt", "jsonld": "https://wpnews.pro/news/metas-spark-muse-1-1-is-now-available-on-databricks-fully-governed-by-unity-ai.jsonld"}}