- Services
MiniMax is the Shanghai lab’s flagship language model family, including MiniMax-Text and MiniMax-M1. Recent releases are open weight and compete on long-context and agent benchmarks.
See all models from MiniMaxModels in family
5
Open weight
2
API only
3
Avg score
61.2
Top benchmark
96.5
TTS Arena
Total HF downloads
437.4K
Primary modality
Text
Context window
205K – 1.0M
First release
Oct 2025
Latest release
Jun 2026
Every release in the MiniMax family, ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | MiniMax Speech 2.6API | audio | AA72.0 | — | Oct 2025 |
| 2 | text | BB62.2 | 230B | Feb 2026 | |
| 3 | MiniMax M2.7API | text | BB59.1 | — | Feb 2026 |
| 4 | MiniMax Music 2.6API | audio | BB57.8 | — | Apr 2026 |
| 5 | text | BB55.0 | 428B | Jun 2026 |
When a family spans multiple modalities, the strongest model in each one.
Text
minimax-m2.5
Audio
MiniMax Speech 2.6
How the family splits across text, image, video, audio, embedding, and decision releases.
When each release shipped, newest first. Useful for tracking version cadence.
Jun 1
Apr 10
Feb 28
Feb 11
Oct 30
Composite grades across this family. Higher is better, blending benchmarks, popularity, and efficiency.
Models with downloadable weights, ranked by composite score.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | text | BB62.2 | 230B | Feb 2026 | |
| 2 | text | BB55.0 | 428B | Jun 2026 |
Closed-source releases accessed through MiniMax’s API.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | MiniMax Speech 2.6API | audio | AA72.0 | — | Oct 2025 |
| 2 | MiniMax M2.7API | text | BB59.1 | — | Feb 2026 |
| 3 | MiniMax Music 2.6API | audio | BB57.8 | — | Apr 2026 |
The MiniMax family is a series of AI models from MiniMax. This page lists every release in the family with its benchmark scores, parameter count, and hardware requirements.
By composite score, minimax-m2.5 is currently the top model in the family. For local inference, match the parameter count to your VRAM budget. For quality, pick the highest scorer that fits.
See the open-weight section above for models you can run locally. The API-only section lists closed releases that must be accessed through the provider’s API.
Spin up an instance in the cloud, or pick local hardware that fits.
Advertising disclosure: we earn commissions when you shop through the links below.
Vast.ai
Decentralized GPU marketplace with the lowest hourly prices.
RunPod
Pay-per-second GPU rentals starting at $0.20/hr.
Digital Ocean
Spin up a GPU droplet in minutes, starting at $0.75/hr.
Vultr
GPU cloud with hourly and monthly plans, starting at $0.50/hr.
GPU Mart
Dedicated GPU servers and VPS billed monthly, starting at $0.50/hr.
PPQ.ai
Multi-model inference gateway for production workloads.
Find Local Hardware
See which GPU, Mac, or workstation can run MiniMax on-prem.
Local LLM Mini PCs
Compact machines that run MiniMax on your desk. Chosen for local inference.
