MiniMax M2.5

by MiniMax · minimax/minimax-m2.5

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

Input / 1M tokens
$0.30
Output / 1M tokens
$1.20
Context
205K

Specs

Input price$0.30 / 1M tokens
Output price$1.20 / 1M tokens
Cached input$0.03 / 1M tokens
Context window205K tokens
Max output131K tokens
Readstext
Writestext
Tool callingYes
ReasoningYes
ListedFeb 12, 2026

List prices in USD, updated Oct 30, 2026. Providers may charge differently.

Providers

8 providers serve this model, as of Oct 30, 2026, 18:12 UTC.

Providers serving this model, sorted by price
ProviderQuantizationContextMax outputInput / 1MOutput / 1MCache read / 1MUptime (30 min)Latency (median)Throughput (median)SupportsStatus
VeniceCheapest—198K32.8K$0.27$0.95$0.03100%1.15 s38 tok/sNormal
StreamLakeFastest—200K128K$0.27$1.08$0.027100%687 ms98 tok/sNormal
AtlasCloudfp8197K177K$0.295$1.20$0.06100%1.49 s92 tok/sNormal
DigitalOcean—65.5K59K$0.30$1.20$0.06—889 ms75 tok/sNormal
GMICloudfp8197K177K$0.30$1.20$0.0366.7%1.64 s35 tok/sNormal
Minimax—205K131K$0.30$1.20$0.03100%1.29 s38 tok/sNormal
Novitafp8205K131K$0.30$1.20$0.03—1.45 s34 tok/sNormal
Minimax—205K131K$0.60$2.40$0.0650%2.21 s32 tok/sNormal

"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.