minimax-m3.1-flash

Name: minimax-m3.1-flash
Author: NVIDIA

proprietary

Frontier multimodal coding model with 1M context window and tunable thinking depth

Context

Input price

$0.15/1M tokens

Output price

$0.6/1M tokens

Capabilities

Show unsupported (6)

Reasoning & Interaction

Tool Calling

Infrastructure

Streaming

Details

Model IDminimaxai/minimax-m3.1-flash

ProviderNVIDIA

CreatorMiniMax

Familyminimax

Licenseproprietary

Statusactive

Typechat

Input modalitiestext

Output modalitiestext

Open weightNo

Parameters—

Architecture—

Context window1M tokens

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date—

Sourceofficial

Pricing

Input

$0.15

Output

$0.6

Cache write

—

Cache read

$0.02

Batch in

—

Batch out

—

Family Comparison: minimax

Model	Caps	Perf	Speed	Context	Max out
minimax-m2.1	TSF	—	—	205K	—
minimax-m2.5	TSF	—	—	205K	—
minimax-m2.7	TS	—	—	205K	—
minimax-m3.1-flash	TS	—	—	1M	—
minimax-m3	TS	—	—	1M	—

API

GET/v1/models/nvidia/minimaxai/minimax-m3.1-flash