Microsoft Foundry is expanding the ways developers and businesses can test, run, and operationalize AI models. The most consequential update is the general availability of Fireworks AI open-model inference in Foundry, which gives customers access through a single Azure endpoint with enterprise SLAs, minimal onboarding, and no separate infrastructure or contracts. Microsoft also points to a broader Foundry strategy that combines a growing model catalog, local inference, and tools for grounding AI applications in organizational data.
The update is not evidence of a separately announced new MAI model release. Instead, it reflects a more practical change in how Microsoft Foundry can be used: teams can explore and deploy a wider range of models through the same platform rather than assembling separate providers, endpoints, and operational arrangements. Microsoft detailed the Fireworks AI release and related platform updates in its official Microsoft Foundry Build 2026 announcement.
What the Microsoft Foundry updates change
Fireworks AI's general availability brings open-model inference into Foundry's Azure-based environment. According to Microsoft, the service is delivered through a single Azure endpoint and includes enterprise SLAs. The practical appeal is consolidation: a team evaluating an open model does not need to separately provision infrastructure or negotiate an additional contract to use it through Foundry.
That matters for businesses moving beyond a proof of concept. Model choice is only one part of an AI project. Access controls, endpoints, uptime expectations, deployment workflows, and data connections can add time and complexity. Foundry's direction is to make those elements available within one Microsoft AI platform while retaining access to a broad set of models.
Microsoft's Foundry catalog and API already include multiple model families, including Claude models and MAI-Image variants. This does not mean every model has identical capabilities, availability, or commercial terms. It does mean developers can use Foundry as a common access layer when selecting models for different tasks.
Fireworks AI, Foundry Labs, and Foundry Local serve different jobs
The current releases address three distinct stages of AI work:
- Fireworks AI inference is for using supported open models through Foundry's Azure endpoint in a production-oriented environment.
- Foundry Labs is a centralized, searchable hub for experiments, with "Try it now" calls to action designed to support evaluation and prototyping.
- Foundry Local is generally available for cross-platform local AI inference, allowing models to run without a cloud dependency and without per-token costs.
| Foundry capability | Primary purpose | Deployment or access approach | Commercial detail confirmed in the research |
|---|---|---|---|
| Fireworks AI open-model inference | Run supported open models through Foundry | Single Azure endpoint with enterprise SLAs | No separate infrastructure or contracts are required |
| Foundry Labs | Explore and prototype AI experiments | Searchable labs.ai.azure.com hub with "Try it now" experiences | No pricing detail is specified in the supplied material |
| Foundry Local | Run AI inference locally | Cross-platform operation without a cloud dependency | No per-token costs |
For a smaller team, the distinction is useful. Foundry Labs can help assess whether an experiment is relevant before it becomes a project. Fireworks AI inference can reduce the friction of taking a selected open model into a managed Azure environment. Foundry Local may be relevant where a cloud dependency is unsuitable or where per-token inference charges are not the preferred cost model. The right route depends on the model, workload, security needs, and existing Microsoft environment.
Integration is the larger platform story
Microsoft positions Foundry as part of a wider AI stack rather than as a standalone model playground. Its materials highlight connections to Fabric IQ, Work IQ, and various connectors. The intended outcome is to let Foundry's unified API and catalog can simplify model access, while the surrounding Microsoft tools and connectors address the data side of the implementation.
This is significant because useful business AI typically depends on more than a capable model. A customer-support assistant, internal knowledge tool, or operations workflow needs access to the right data and systems. Foundry's unified API and catalog can simplify model access, while the surrounding Microsoft tools and connectors address the data side of the implementation.
Businesses should still treat integration as a design task, not a switch to flip. The supplied information confirms that Microsoft is highlighting these connections, but it does not establish that every data source, model, or workflow is automatically compatible. Teams should define the specific process they want to improve, identify the data required, and test whether the chosen model and connection pattern produce dependable results.
Microsoft's public updates also do not provide a single universal price for Fireworks AI inference or the full Foundry catalog. The confirmed pricing-related distinction is that Foundry Local has no per-token costs. Organizations comparing options should therefore verify the applicable commercial terms for their selected model and deployment method before committing to an implementation.
For companies already using Microsoft tools, the opportunity is to reduce fragmentation. Instead of managing separate routes for experimentation, model access, local testing, and data-aware AI applications, Foundry is increasingly positioned as a central environment for those activities. That can make pilots easier to structure, but a pilot should still be measured against a concrete operational outcome such as less manual research, faster document handling, or better access to internal knowledge.
If your team wants to turn model experimentation into a reliable workflow, Scalevise can help assess the right use case, data connections, and implementation path. Our practical AI consultancy for business adoption focuses on selecting tools that fit real operations, avoiding disconnected proofs of concept, and building an achievable roadmap around your existing systems. Request a consultation to map a Microsoft Foundry opportunity to a measurable business process.
Frequently Asked Questions
What is new in Microsoft Foundry?
Microsoft has made Fireworks AI open-model inference generally available in Foundry. It is delivered through a single Azure endpoint with enterprise SLAs, minimal onboarding, and no separate infrastructure or contracts.
Is Microsoft Foundry Local generally available?
Yes. Foundry Local has reached general availability and supports cross-platform local AI inference without a cloud dependency or per-token costs.
Does the update confirm a new MAI model release?
No. The supplied research confirms broader model catalog access, including MAI-Image variants, but does not identify a separately announced new MAI model release.
How does Microsoft Foundry connect to other Microsoft AI tools?
Microsoft highlights Foundry's relationship with Fabric IQ, Work IQ, and connectors that can help ground agents and AI applications in organizational data sources.
Conclusion
Microsoft Foundry's latest updates make the platform more useful across experimentation, managed open-model inference, and local deployment. Fireworks AI availability is the clearest production-oriented addition, while Foundry Labs and Foundry Local give teams more ways to evaluate and run AI workloads. The key business question is not simply which model to try, but which workflow and data connection can turn that access into a useful result.
Top comments (0)