Models / MiniMax AI

MiniMax AI

Deploy the latest MiniMax models on Together AI, a preferred cloud partner for MiniMax. Frontier coding, a million-token context, and native multimodality in open weights.

Why MiniMax AI on Together AI?

Designed for production workloads that need 
consistent performance and operational control.

Long context without the compute penalty

MiniMax Sparse Attention (MSA) sharply reduces per-token compute at long context, with large prefill and decode speedups. Long agent runs, extended coding sessions, and long-video understanding stay affordable.

Coding, agents, and multimodality

MiniMax models combine frontier coding, agentic capability, and native image and video input in a single open-weight checkpoint. Toggle thinking mode at request time, no separate model version required.

Enterprise-ready from day one

SOC 2 Type II certified, HIPAA compliant, and deployed on US-based infrastructure. Full model ownership with no data retention by default.

Meet the MiniMax AI family

Explore top-performing models across text, image, video, code, and voice.

Chat

MiniMax M3

Audio

MiniMax Speech 2.8

Audio

MiniMax Speech 2.6 Turbo

Chat

MiniMax M1 40K

Chat

MiniMax M2.1

Chat

MiniMax M2.5

Chat

MiniMax M2.7

Chat

MiniMax M1 80K

Video

MiniMax Hailuo 02

Video

MiniMax 01 Director

Deployment options

Run models using different deployment options depending on latency needs, traffic patterns, and infrastructure control.

  • Serverless Inference

  • Provisioned 
Throughput

  • Dedicated Model 
Inference

  • Dedicated Container 
Inference

Serverless Inference

A fully managed real-time or batch inference API with access to dozens of the most popular AI models.

Best for

Variable or unpredictable traffic

Rapid prototyping and iteration

Cost-sensitive or early-stage production workloads

Provisioned 
Throughput

Reserved token capacity with SLA guarantees. Priced in PTUs, a normalized throughput unit. 

Best for

Production workloads

Reliability guarantees

Predictable pricing

Dedicated Model 
Inference

An inference endpoint backed by reserved, isolated compute resources and Together AI inference research.

Best for

Predictable or steady traffic

Latency-sensitive applications

High-throughput production workloads

Dedicated Container 
Inference

Run inference with your own engine and model on fully-managed, scalable infrastructure.

Best for

Generative media models

Non-standard runtimes

Custom inference pipelines