Command A+ vs MAI-Thinking-1

Cohere · Canada  |  Microsoft · US · Updated June 2026

Quick verdict

Pick Command A+ for cohere's newer, more efficient flagship - runs on just two h100 gpus, unusually lean for a 218b-parameter model or a 218b-total/25b-active moe released with open weights (apache 2.0) on hugging face. Pick MAI-Thinking-1 for very strong math reasoning (aime 2025 97%, aime 2026 94.5%) or microsoft's first in-house flagship reasoner, trained without openai distillation. Choose Command A+ if you need self-hosting or data privacy; MAI-Thinking-1 if you want a managed API.

Command A+ (Cohere, Canada) and MAI-Thinking-1 (Microsoft, US) line up two different AI ecosystems against each other — a comparison that is as much about cost philosophy and openness as raw capability. Command A+ is cohere's newer, leaner flagship - a 218B open-weight MoE tuned for efficiency (just two GPUs to run) and 48-language support. MAI-Thinking-1 is microsoft's first fully in-house flagship reasoning model — a Claude-class reasoner built independently to cut its OpenAI dependence. Their biggest split is open vs. closed weights, and the breakdown below shows exactly how that plays out for your workload.

Key differences at a glance

Side-by-side specs

SpecCommand A+MAI-Thinking-1
ProviderCohere (Canada) Microsoft (US)
ReleasedMay 19, 2026 August 12, 2026
Context window256K (unconfirmed) (~384 pages) 256K (~384 pages)
Price (in/out)Open weight (self-host / free) Not published
Open weight?Yes — self-hostable No — API only
Modalitiestext, code text, code
SWE-Bench VerifiedNot published Not published
MRCR v2 @ 1MNot published Not published

Who wins what

Cohere's newer, more efficient flagship - runs on just two H100 GPUs, unusually lean for a 218B-parameter model

Command A+

Cohere's newer, leaner flagship - a 218B open-weight MoE tuned for efficiency (just two GPUs to run) and 48-language support — and its weights are open while MAI-Thinking-1 is API-only.

A 218B-total/25B-active MoE released with open weights (Apache 2.0) on Hugging Face

Command A+

Open weights make this possible at all — MAI-Thinking-1 is API-only, so it cannot leave the vendor's servers.

Supports 48 languages, including all official EU languages

Command A+

Command A+ lists supports 48 languages, including all official EU languages among its strengths; MAI-Thinking-1 does not.

Very strong math reasoning (AIME 2025 97%, AIME 2026 94.5%)

MAI-Thinking-1

Command A+ is comparatively weak here — enterprise/multilingual focus rather than topping general reasoning leaderboards

Microsoft's first in-house flagship reasoner, trained without OpenAI distillation

MAI-Thinking-1

Command A+ is comparatively weak here — newer release with less independent benchmark verification than established flagships

Efficient reasoning at low token cost for its class

MAI-Thinking-1

Command A+ is comparatively weak here — no official context window or per-token price published yet - both are estimated/unavailable

Which should you pick?

A team with data-privacy or self-hosting needs

Command A+

Open weights let you run it on your own hardware; MAI-Thinking-1 is API-only.

Anyone whose priority is cohere's newer, more efficient flagship - runs on just two h100 gpus, unusually lean for a 218b-parameter model

Command A+

It is specifically built for that.

Anyone whose priority is very strong math reasoning (aime 2025 97%, aime 2026 94.5%)

MAI-Thinking-1

That is its strongest area.

An enterprise with regional data-residency rules

MAI-Thinking-1 or Command A+

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

Command A+: where it fits

Cohere's newer, leaner flagship - a 218B open-weight MoE tuned for efficiency (just two GPUs to run) and 48-language support. Released May 19, 2026 by Cohere, it is built for cohere's newer, more efficient flagship - runs on just two H100 GPUs, unusually lean for a 218B-parameter model, a 218B-total/25B-active MoE released with open weights (Apache 2.0) on Hugging Face, supports 48 languages, including all official EU languages, and positioned by Cohere as its 'most efficient and performant model to date'.

Its trade-offs are real: no official context window or per-token price published yet - both are estimated/unavailable, newer release with less independent benchmark verification than established flagships, and enterprise/multilingual focus rather than topping general reasoning leaderboards. As an open-weight model, its running cost is your own hardware rather than a per-token fee.

MAI-Thinking-1: where it fits

Microsoft's first fully in-house flagship reasoning model — a Claude-class reasoner built independently to cut its OpenAI dependence. Released August 12, 2026 by Microsoft, it is built for very strong math reasoning (AIME 2025 97%, AIME 2026 94.5%), microsoft's first in-house flagship reasoner, trained without OpenAI distillation, efficient reasoning at low token cost for its class, and competitive with Claude Opus 4.6 on SWE-Bench Pro (vendor-reported).

Its trade-offs: closed and in private preview — no open weights, no published pricing, thin availability, and benchmarks are largely self-reported.

The bottom line for this matchup

The defining split here is open vs. closed. Command A+ gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. MAI-Thinking-1 gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.

Want both Command A+ and MAI-Thinking-1 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 Command A+ or MAI-Thinking-1 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, Command A+ leans toward cohere's newer, more efficient flagship - runs on just two h100 gpus, unusually lean for a 218b-parameter model while MAI-Thinking-1 leans toward very strong math reasoning (aime 2025 97%, aime 2026 94.5%), and that positioning usually predicts which feels better on your codebase.

Which is cheaper, Command A+ or MAI-Thinking-1?

Command A+ is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while MAI-Thinking-1 is API-metered at Not published. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.

Which has the bigger context window?

Both advertise 256K (unconfirmed) (~384 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.

Can I use both Command A+ and MAI-Thinking-1 together?

Yes — a multi-model platform like LumiChats gives you Command A+, MAI-Thinking-1 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, Command A+ or MAI-Thinking-1?

MAI-Thinking-1 — released August 12, 2026, about 3 months after Command A+.

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.