MiniMax-M3.1-Flash

minimax-m3.1-flash

Everyday flagship model for real work

MiniMax-M3.1-Flash launched on 2026-10-19 and is the current text model on M Plan and pay-as-you-go. MiniMax describes it as a native multimodal model with a 1M context window and adjustable thinking depth, for coding, agents, and computer use. Pay-as-you-go pricing is ¥1/M input, ¥4/M output, and ¥0.1/M cache read. The Preview name is retired; those requests are served by this model (verified 2026-10-20).

1M context1M context

Released2026-10-19

Relays21 sites

multimodallong contextreasoningtool use

Model information

Model ID: minimax-m3.1-flash
Context: 1M
Max input: -
Max output: 512K
Knowledge cutoff: -
Open weights: Supported
License: -
Release date: 2026-10-19

Input

Text: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported

Output

Text: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported

API capabilities

Reasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported

MiniMax Official Pricing

CNY

Updated: 2026-10-19T17:13:06.071+08:00

Input

~¥1.003/ 1M tokens

Output

~¥4.012/ 1M tokens

Cache read

~¥0.1003/ 1M tokens

Relay Comparison

Compare token, per-request, or per-second pricing by relay channel.

Unit: token prices are ¥ / 1M tokens; per-request and per-second rows use their shown unit

9527code

https://9527.codesToken billing

Price range ¥0.6 / 1M tokens

Cache hit¥0.06

国产官方模型

Cache hit¥0.06

Channel	Billing	Input	Output	Cache hit	Cache write
MiniMax	Token	¥0.6	¥2.4	¥0.06	-
国产官方模型	Token	¥0.6	¥2.4	¥0.06	-

8sToken

8stoken.comToken billing

Price range ¥2.1 / 1M tokens

国产模型聚合专区

Cache hit¥0.42

Channel	Billing	Input	Output	Cache hit	Cache write
国产模型聚合专区	Token	¥2.1	¥4.2	¥0.42	-

天天中转站

https://apitiantian.comToken billing

Price range ¥0.15 / 1M tokens

国模2折福利

Cache hit¥0.01

国模福利-chat端点

Cache hit¥0.01

国模福利-messages端点

Cache hit¥0.01

Channel	Billing	Input	Output	Cache hit	Cache write
国模2折福利	Token	¥0.15	¥0.6	¥0.01	¥0
国模福利-chat端点	Token	¥0.15	¥0.6	¥0.01	¥0
国模福利-messages端点	Token	¥0.15	¥0.6	¥0.01	¥0

OmniaKey

omniakey.comToken billing

Price range ¥0.504 / 1M tokens

Cache hit¥0.054

Channel	Billing	Input	Output	Cache hit	Cache write
default	Token	¥0.504	¥2.01	¥0.054	-

Token 88

t8api.comToken billing

Price range ¥2.1 / 1M tokens

国产模型聚合

Cache hit¥0.42

Channel	Billing	Input	Output	Cache hit	Cache write
国产模型聚合	Token	¥2.1	¥4.2	¥0.42	-

找模型

api.zhaomoxing.comToken billing

Price range ¥4.5 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
国模福利	Token	¥4.5	¥4.5	-	-

智流 FluxLane

fluxlane.cnToken billing

Price range ¥0.45 / 1M tokens

MiniMax-Pro｜官转专线

Cache hit¥0.045

Channel	Billing	Input	Output	Cache hit	Cache write
MiniMax-Pro｜官转专线	Token	¥0.45	¥1.8	¥0.045	-

MuMuMix

mumumix.comToken billing

Price range ¥0.15 / 1M tokens

Cache hit¥0.015

Channel	Billing	Input	Output	Cache hit	Cache write
国模-综合	Token	¥0.15	¥0.6	¥0.015	¥0

LinoRoute

linoroute.comToken billing

Price range ¥0.099 - ¥0.2475 / 1M tokens

Self-Deployed-1

Cache hit¥0.0099

Self-Deployed-2

Cache hit¥0.0165

Self-Deployed-3

Cache hit¥0.0248

Channel	Billing	Input	Output	Cache hit	Cache write
Self-Deployed-1	Token	¥0.099	¥0.396	¥0.0099	-
Self-Deployed-2	Token	¥0.165	¥0.66	¥0.0165	-
Self-Deployed-3	Token	¥0.2475	¥0.99	¥0.0248	-

XycAi(星道智能)

https://xycai.us/Token billing

Price range ¥0.5421 / 1M tokens

MiniMax 企业版

Cache hit¥0.0542

Channel	Billing	Input	Output	Cache hit	Cache write
MiniMax 企业版	Token	¥0.5421	¥2.17	¥0.0542	¥0

How should MiniMax-M3.1-Flash relay pricing be compared?

This MiniMax-M3.1-Flash pricing page compares official pricing with public prices from 21 listed AI gateways. Token prices are shown in CNY per 1M tokens, while per-request, per-second, and per-character rows use the unit shown in the table. Last updated: 11/08/2026, 08:15.

Data sources: Public price catalogs, official pricing records, and monitoring results.
Metric definitions: Uptime means successful probe response rate, fake-rate signals possible model mismatch or abnormal output risk, and latency is average API response time.
Risk note: Relay gateways are third-party services. Pricing, billing, privacy, and stability can change; start with a small top-up and verify reliability before continued use.