MAI-Thinking-1

How can you access MAI-Thinking-1?

The catalog documents API access for MAI-Thinking-1. Source

As of the catalog check, this version was listed as a preview. Source

For API use, confirm the exact model identifier, your account and region, and the endpoint's current limits in the linked documentation. An API listing does not establish access through a consumer subscription.

Which MAI-Thinking-1 does this page describe?

MAI-Thinking-1 is a model record from Microsoft in the MAI family. Source

The recorded model identifier or checkpoint is MAI-Thinking-1. Use that exact identifier when checking documentation or a provider listing. Source

How much does MAI-Thinking-1 cost?

The recorded token rates for MAI-Thinking-1 are:

• Input: US$2 per 1 million input tokens. Source
• Output: US$8 per 1 million output tokens. Source

Rate conditions: Microsoft Foundry public-preview list pricing: USD per million input/output tokens. The card quotes $2 input and $8 output; separate preview and deployment terms apply. Source

Illustrative arithmetic: 10,000 input tokens plus 2,000 output tokens would cost US$0.036 at those recorded rates. This assumes every token is billed at the displayed rate and excludes any cache, batch, tool, storage or tier adjustments; it is not a quote or measured usage.

Check the source's pricing conditions before budgeting. A token rate does not state the price of an app subscription or the full cost of running downloaded weights.

What are MAI-Thinking-1's context and output limits?

The publisher reports the context window as 256K tokens. Source We retain the publisher's notation and qualifiers; no exact token count or hosted serving allowance is inferred from it.

A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance.

Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity.

What dates are documented for MAI-Thinking-1?

Training-data cutoff: July 2026. Source This describes the reported data boundary, not the day training finished. The source labels this “Publisher training cut-off date.”

Retrieval or web tools can supply newer information at run time. That does not change the model's recorded training or knowledge dates, and this record does not establish that a particular endpoint includes those tools.

What can MAI-Thinking-1 receive and generate?

Documented inputs: text. Source

Documented outputs: text. Source

Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation.

What distinguishes MAI-Thinking-1?

These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results.

Architecture

Microsoft describes a mixture-of-experts model with about one trillion total parameters and 35 billion active parameters. These are publisher-reported counts, not measured inference memory. Source

Access status

The official model page offers MAI-Thinking-1 in public preview through Microsoft Foundry. Source

Integration responsibility

Microsoft describes Chat Completions integration, but says the model has no native tool interface: the integrating application mediates tools and is responsible for their security boundary. Text-only input/output does not imply image, audio or video support. Source