Models/MiniMax/MiniMax M1

MiniMax M1

Name: MiniMax M1 API access
Brand: MiniMax

MiniMax · Proprietary · Released Jun 17, 2025 · minimax/minimax-m1

Compare Estimate cost

1M contextToolsReasoning

Available from 2 providersUSD / MTOK · VERIFIED 4 MINUTES AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
Minimax1ST PARTY	$0.40	$2.20	—	1M	—	1.2s	79 tok/s	100.0%
Novita	$0.55	$2.20	—	1M	bf16	1.6s	85 tok/s	100.0%

TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 44 hours ago

About

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

Context window1,000,000

Max output40,000

Modalities intext

Modalities outtext

LicenseProprietary

ReleasedJun 17, 2025

Knowledge cutoff2024-06-30

TokenizerOther

MiniMax M3$0.23 / $0.96 MiniMax M2.7$0.24 / $0.96 MiniMax M2.5$0.27 / $0.95 MiniMax M2-her$0.30 / $1.20

Embed badge

[![MiniMax M1](https://modelindex.ai/badge/minimax/minimax-m1)](https://modelindex.ai/models/minimax/minimax-m1)

Sources

OpenRouter API4 minutes ago

AGGREGATOR

ModelIndex benchmarks44 hours ago

MEASURED

Verified 4 minutes ago · list prices, not negotiated rates.