modelgrep

Longest-Context MiniMax Models

Quick answer · Updated June 2026

MiniMax M3 has the largest context window of any MiniMax model, at 1.0M tokens. MiniMax-01 (1.0M) and MiniMax M1 (1M) round out the top three.

1.0MContext
54.7Intelligence
42 t/sSpeed
$0.300Input /M

AI models with the largest context windows, ranked by token capacity. The best large language models for long documents, codebases and extended conversations.

  1. 1M
    minimax-m3
    ReasoningToolsJSON+154.7 intel · $0.300/M · 42 t/s
    1.0M
    Context
  2. 2M
    minimax-01
    Vision$0.200/M · 34 t/s · 823ms ttft
    1.0M
    Context
  3. 3M
    minimax-m1
    ReasoningTools$0.400/M · 18 t/s · 840ms ttft
    1M
    Context
  4. 4M
    minimax-m2.7
    ReasoningToolsJSON49.6 intel · $0.250/M · 273 t/s
    205K
    Context
  5. 5M
    minimax-m2.5
    ReasoningToolsJSON41.9 intel · $0.150/M · 183 t/s
    205K
    Context
  6. 6M
    minimax-m2.1
    ReasoningToolsJSON39.4 intel · $0.290/M · 149 t/s
    205K
    Context
  7. 7M
    minimax-m2
    ReasoningToolsJSON36.1 intel · $0.255/M · 103 t/s
    205K
    Context

Frequently asked

Which MiniMax model has the largest context window?

MiniMax M3 has the largest context window of any MiniMax model, at 1.0M tokens. MiniMax-01 (1.0M) and MiniMax M1 (1M) round out the top three.

What's a good alternative to MiniMax M3?

MiniMax-01 (1.0M) is the closest alternative on this metric, followed by MiniMax M1 (1M). See the full ranking above for the tradeoffs.

How many MiniMax models are there?

modelgrep tracks 8 MiniMax models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by MiniMax M3. 7 of them qualify for this ranking.

More MiniMax rankings

All rankings