MiniMax M3

minimax-m3

A multimodal model for long-context coding, perception, and agent planning.

MiniMax multimodal model for long-context coding, perception, and agent planning

1M context1M context

Released2026-06-01

Relays41 sites

multimodallong contextcode generationreasoning

Model information

Model ID: minimax-m3
Context: 1M
Max input: -
Max output: 512K
Knowledge cutoff: -
Open weights: Supported
License: -
Release date: 2026-06-01

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: 2026-10-04T22:55:12.149+08:00

Input

~¥2.007/ 1M tokens

Output

~¥8.027/ 1M tokens

Cache read

~¥0.4014/ 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

88API Token聚合平台

https://88api.ai/sign-up?aff=po46Token billing

Price range ¥1.05 - ¥1.47 / 1M tokens

Cache hit¥0.21

Cache hit¥0.294

Channel	Billing	Input	Output	Cache hit	Cache write
Minimax开源	Token	¥1.05	¥4.2	¥0.21	-
Minimax官转	Token	¥1.47	¥5.88	¥0.294	-

9527code

https://9527.codesToken billing

Price range ¥0.42 / 1M tokens

Cache hit¥0.084

Channel	Billing	Input	Output	Cache hit	Cache write
free	Token	¥0.42	¥1.68	¥0.084	-

智惠API

api.api2cn.comToken billing

Price range ¥0.315 / 1M tokens

国产模型组合

Cache hit¥0.063

Channel	Billing	Input	Output	Cache hit	Cache write
国产模型组合	Token	¥0.315	¥1.26	¥0.063	¥0

OmniaKey

omniakey.comToken billing

Price range ¥1.24 / 1M tokens

Cache hit¥1.92

Cache write¥0.096

Channel	Billing	Input	Output	Cache hit	Cache write
default	Token	¥1.24	¥0.48	¥1.92	¥0.096

aiaimark

https://www.aiaimark.comToken billing

Price range ¥3.78 / 1M tokens

Cache hit¥0.756

Channel	Billing	Input	Output	Cache hit	Cache write
MiniMax	Token	¥3.78	¥15.12	¥0.756	¥0

PackyCode

packyapi.aiToken billing

Price range ¥2.1 / 1M tokens

minimax-officially

Cache hit¥0.42

Channel	Billing	Input	Output	Cache hit	Cache write
minimax-officially	Token	¥2.1	¥8.4	¥0.42	-

天天中转站

https://apitiantian.comToken billing

Price range ¥0.4 / 1M tokens

国模2折福利

Cache hit¥0.08

国模福利-chat端点

Cache hit¥0.08

国模福利-messages端点

Cache hit¥0.08

Channel	Billing	Input	Output	Cache hit	Cache write
国模2折福利	Token	¥0.4	¥1.6	¥0.08	¥0
国模福利-chat端点	Token	¥0.4	¥1.6	¥0.08	¥0
国模福利-messages端点	Token	¥0.4	¥1.6	¥0.08	¥0

Moniker

aimoniker.topToken billing

Price range ¥0.42 - ¥0.84 / 1M tokens

Cache hit¥0.084

国产模型-oai

Cache hit¥0.168

Channel	Billing	Input	Output	Cache hit	Cache write
国模福利	Token	¥0.42	¥1.68	¥0.084	-
国产模型-oai	Token	¥0.84	¥3.36	¥0.168	-

找模型

api.zhaomoxing.comToken billing

Price range ¥7.5 / 1M tokens

国模-稳定-极速

Channel	Billing	Input	Output	Cache hit	Cache write
国模-稳定-极速	Token	¥7.5	¥7.5	-	-

天枢

tian-shu.netToken billing

Price range ¥1.4 / 1M tokens

Cache hit¥0.147

Channel	Billing	Input	Output	Cache hit	Cache write
minimax	Token	¥1.4	¥2.94	¥0.147	-

How should MiniMax M3 relay pricing be compared?

This MiniMax M3 pricing page compares official pricing with public prices from 41 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: 10/23/2026, 08:16.

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.