Skip to content
LLMs
MiniMax logo

MiniMax: MiniMax M1

by MiniMax

MiniMax: MiniMax M1 is a large language model from MiniMax. It costs $0.550 per million input tokens and $2.20 per million output tokens. Its context window is 1M tokens.

ReasoningTool calling
Input / 1M tokens
$0.550
Output / 1M tokens
$2.20
Cached input / 1M
-

Not supported

Context window
1M

tokens

Who serves it cheapest

2 hosts serve MiniMax M1. Same weights, same API - the price difference is pure margin and routing.

Providers serving MiniMax: MiniMax M1, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
MinimaxCheapest$0.400$2.201M-100.0%
Novitabf16$0.550$2.201M-100.0%

The spread between Minimax and Novita is 1.1× for identical weights. Quantization and context limits differ, so check both columns before switching.

About MiniMax M1

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...

Specifications

MiniMax: MiniMax M1 specifications
Model IDminimax/minimax-m1
ProviderMiniMax
Context window1M tokens
Max output40K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2024-06-30
Open weightsNo
ReleasedJune 17, 2025

Cheaper alternatives

Models that cost less than MiniMax M1 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does MiniMax: MiniMax M1 cost?

$0.550 per million input tokens and $2.20 per million output tokens.

What is the context window of MiniMax: MiniMax M1?

1M tokens, with up to 40K tokens of output per request.

Which provider serves MiniMax: MiniMax M1 cheapest?

Minimax at $0.400 per million input tokens - 1.1× cheaper than Novita, the most expensive of the 2 hosts serving it.

Confirm against the source: MiniMax official pricing.