Skip to content

MiniMax M2.5

MiniMax M2.5 is a third-generation agentic model from MiniMax that handles full-stack development across Web, Android, iOS, Windows, and Mac platforms. It supports a context window of 1M tokens, a max output of 196K tokens, and completes tasks about 37% faster than M2.1.

ReasoningTool UseImplicit Caching
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'minimax/minimax-m2.5',
prompt: 'Why is the sky blue?'
})

More models by MiniMax

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Per Query
Capabilities
Providers
ZDR
No Training
Release Date
205K
0.3s
214tps
$0.24/M$0.96/M
Read:$0.06/M
Write:$0.38/M
blackbox logo
fireworks logo
minimax logo
+2
03/18/2026
205K
1.3s
45tps
$0.60/M$2.40/M
Read:$0.06/M
Write:$0.38/M
minimax logo
03/18/2026
205K
1.1s
46tps
$0.60/M$2.40/M
Read:$0.03/M
Write:$0.38/M
minimax logo
novita logo
02/12/2026
205K
0.4s
159tps
$0.30/M$1.20/M
Read:$0.03/M
Write:$0.38/M
bedrock logo
minimax logo
novita logo
10/27/2025
205K
0.7s
66tps
$0.30/M$1.20/M
Read:$0.03/M
Write:$0.38/M
minimax logo
novita logo
10/27/2025
205K
1.0s
48tps
$0.30/M$2.40/M
Read:$0.03/M
Write:$0.38/M
minimax logo
10/27/2025