🇨🇳 Chinese model

MiniMax-M2.5

Text Function calling Reasoning

Pricing & specs

Input / 1M tokens $0.30

Output / 1M tokens $1.20

Cache / 1M tokens —

Context window 205K tokens

Max output 131K tokens

Updated 2026-02-12

Docs Official docs ↗

Price source View source ↗

Providers

USD / 1M tokens · input / output

MiniMax Official $0.30 / $1.20 Deep Infra lowest $0.15 / $1.15 CloudFerro Sherlock $0.30 / $1.20 Baseten $0.30 / $1.20 SiliconFlow $0.30 / $1.20 302.AI $0.30 / $1.20 SiliconFlow (China) $0.30 / $1.22

6 more at higher prices

Plans / subscriptions

Alibaba Coding Plan Included in plan Alibaba Coding Plan (China) Included in plan Alibaba Token Plan Included in plan Alibaba Token Plan (China) Included in plan SCNet Token Plan Included in plan

Similar models · Top 5

GLM-4.7 🇨🇳 205K In $0.30 · Out $1.19 · Cache $0.06 Qwen3 32B 🇨🇳 131K In $0.29 · Out $1.15 · Cache — Qwen3 235B-A22B 🇨🇳 131K In $0.29 · Out $1.15 · Cache — siliconflow/deepseek-v3.1-terminus 🇨🇳 164K In $0.27 · Out $1.00 · Cache — siliconflow/deepseek-v3-0324 🇨🇳 164K In $0.25 · Out $1.00 · Cache —

Want to go deeper on AI and cloud cost management?

Explore more on AI infrastructure, model API cost and resource optimization at mofcloud.

Go to mofcloud Back to price explorer