Project AURIONAI Use-Cases Research & Innovation
MiniMax
reasoning

MiniMax-M1

MiniMax reasoning model with a published RL-stage cost anchor.

MiniMaxMiniMaxChinaMiniMax-MFamily
Figure from the MiniMax-M1 paper: token probabilities in training mode against inference mode.
Levelmodel
Classreasoning
Parameters456B
Contextnot in the notes
Released16 Jun 2025
Opennessunknown
Runs onnot in the notes
Statusactive

Lineage

successor
MiniMax-M1 to MiniMax-M2: successor, medium confidenceMiniMax-M2 to MiniMax-M2.1: successor, medium confidenceMiniMax-M1MiniMax-M1MiniMax, Jun 2025MiniMax-M2MiniMax-M2MiniMaxMiniMax-M2.1MiniMax-M2.1MiniMax
MiniMaxMiniMax-M2 is a child (successor)medium confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.

R&D Topics

Reasoning via large-scale RLproduced by

Identity

Developer
MiniMax
Family
MiniMax-M
Released
16 Jun 2025 sourcesnotes
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
not in the notes
Total parameters
456B sources
Active parameters
45.9B
Checkpoint parameters
–
Note
Final RL stage $534,700 rental on 512 H800 GPUs for about 3 weeks.
Context length
not in the notes
Input
text
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. MiniMax M3 - Coding & Agentic Frontier, 1M Context, Multimodal minimax.io https://www.minimax.io/models/text/m3
  2. huggingface.co/MiniMaxAI https://huggingface.co/MiniMaxAI
  3. leaderboard.steel.dev/leaderboards/swe-bench-verified.md https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md
  4. MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention arxiv.org https://arxiv.org/abs/2506.13585

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MiniMax-M1", https://aurion.semai.id/models/minimax-minimax-m1/, records of October 2026.