MAI-1-preview vs Mistral Medium 3

Microsoft · US  |  Mistral AI · France · Updated June 2026

Quick verdict

Pick MAI-1-preview for microsoft's first fully in-house, end-to-end foundation model - a historic break from relying solely on openai or ranked in the top 15 on lm arena at launch. Pick Mistral Medium 3 for strong cost-to-capability at $0.40/$2.00 or general reasoning, coding and multimodal tasks. On a tight budget at scale, MAI-1-preview is the value pick.

MAI-1-preview (Microsoft, US) and Mistral Medium 3 (Mistral AI, France) line up two different AI ecosystems against each other — a comparison that is as much about cost philosophy and openness as raw capability. MAI-1-preview is microsoft's first fully in-house foundation model - a strategic break from sole reliance on OpenAI, trained on ~15,000 H100 GPUs. Mistral Medium 3 is mistral's mid-tier model at $0.40/$2.00 — efficient general capability with a 128K window, below the 1M-context frontier tier. Their biggest split is price, and the breakdown below shows exactly how that plays out for your workload.

Key differences at a glance

Side-by-side specs

SpecMAI-1-previewMistral Medium 3
ProviderMicrosoft (US) Mistral AI (France)
ReleasedAugust 28, 2025 May 7, 2025
Context window128K (~192 pages) 128K (~192 pages)
Price (in/out)Not published $0.4/$2 per 1M tokens
Open weight?No — API only No — API only
Modalitiestext, code text, image, code
SWE-Bench VerifiedNot published Not published
MRCR v2 @ 1MNot published Not published

Who wins what

Microsoft's first fully in-house, end-to-end foundation model - a historic break from relying solely on OpenAI

MAI-1-preview

Mistral Medium 3 is comparatively weak here — a mid-tier model, not a frontier reasoner

Ranked in the top 15 on LM Arena at launch

MAI-1-preview

Microsoft's first fully in-house foundation model - a strategic break from sole reliance on OpenAI, trained on ~15,000 H100 GPUs — and it is the newer of the two.

Trained on roughly 15,000 NVIDIA H100 GPUs, a genuine internal infrastructure investment

MAI-1-preview

MAI-1-preview lists trained on roughly 15,000 NVIDIA H100 GPUs, a genuine internal infrastructure investment among its strengths; Mistral Medium 3 does not.

Strong cost-to-capability at $0.40/$2.00

Mistral Medium 3

Mistral Medium 3 lists strong cost-to-capability at $0.40/$2.00 among its strengths; MAI-1-preview does not.

General reasoning, coding and multimodal tasks

Mistral Medium 3

MAI-1-preview is comparatively weak here — distinct from Microsoft's later MAI-Thinking-1 reasoning model - an earlier, more general-purpose entry

Efficient mid-tier deployment for production workloads

Mistral Medium 3

Mistral Medium 3 lists efficient mid-tier deployment for production workloads among its strengths; MAI-1-preview does not.

Lowest cost at scale

MAI-1-preview

Its weights are open, so at volume you pay for your own hardware instead of Mistral Medium 3's $0.4/$2 per 1M tokens.

Which should you pick?

A cost-sensitive startup shipping high volume

MAI-1-preview

At Not published it undercuts Mistral Medium 3, and on millions of tokens that margin decides the monthly bill.

Anyone whose priority is microsoft's first fully in-house, end-to-end foundation model - a historic break from relying solely on openai

MAI-1-preview

It is specifically built for that.

Anyone whose priority is strong cost-to-capability at $0.40/$2.00

Mistral Medium 3

That is its strongest area.

An enterprise with regional data-residency rules

MAI-1-preview or Mistral Medium 3

Origin (US vs France) affects where data is processed and which compliance regime applies — check the provider's terms for your region.

MAI-1-preview: where it fits

Microsoft's first fully in-house foundation model - a strategic break from sole reliance on OpenAI, trained on ~15,000 H100 GPUs. Released August 28, 2025 by Microsoft, it is built for microsoft's first fully in-house, end-to-end foundation model - a historic break from relying solely on OpenAI, ranked in the top 15 on LM Arena at launch, trained on roughly 15,000 NVIDIA H100 GPUs, a genuine internal infrastructure investment, and rolled into Copilot alongside OpenAI models, giving Microsoft a real second option.

Its trade-offs are real: a 'preview' release, not yet positioned as Microsoft's primary Copilot model, no public per-token API pricing - not sold as a standalone product, and distinct from Microsoft's later MAI-Thinking-1 reasoning model - an earlier, more general-purpose entry.

Mistral Medium 3: where it fits

Mistral's mid-tier model at $0.40/$2.00 — efficient general capability with a 128K window, below the 1M-context frontier tier. Released May 7, 2025 by Mistral AI, it is built for strong cost-to-capability at $0.40/$2.00, general reasoning, coding and multimodal tasks, efficient mid-tier deployment for production workloads, and text and image input.

Its trade-offs: a 128K context — smaller than the 1M-window flagships here, no published SWE-Bench Verified score, a mid-tier model, not a frontier reasoner, and proprietary, unlike Mistral's open-weight releases. At $0.4 in / $2 out per million tokens, it sits in the budget price band.

The bottom line for this matchup

This is less "which is smarter" and more "which ecosystem fits." MAI-1-preview (US) and Mistral Medium 3 (France) differ on pricing philosophy, data-residency, and tooling as much as on raw scores. MAI-1-preview is the cheaper option, which matters at volume. The pragmatic move is to run one real task through both and judge the outputs against your own constraints — including where your data is allowed to be processed.

Want both MAI-1-preview and Mistral Medium 3 without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.

See pricing

Frequently asked questions

Is MAI-1-preview or Mistral Medium 3 better for coding?

Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, MAI-1-preview leans toward microsoft's first fully in-house, end-to-end foundation model - a historic break from relying solely on openai while Mistral Medium 3 leans toward strong cost-to-capability at $0.40/$2.00, and that positioning usually predicts which feels better on your codebase.

Which is cheaper, MAI-1-preview or Mistral Medium 3?

MAI-1-preview is cheaper — Not published vs $0.4/$2 per 1M tokens.

Which has the bigger context window?

Both advertise 128K (~192 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.

Can I use both MAI-1-preview and Mistral Medium 3 together?

Yes — a multi-model platform like LumiChats gives you MAI-1-preview, Mistral Medium 3 and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.

Which is newer, MAI-1-preview or Mistral Medium 3?

MAI-1-preview — released August 28, 2025, about 4 months after Mistral Medium 3.

Related comparisons

Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.