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?'})Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
 MiniMax | 205K | 3.2s | 291tps | $0.30/M | $1.20/M | Read:$0.03/M Write:$0.38/M | — | — | +1 | 02/12/2026 | ||
 Nebius | 196K | 0.9s | 98tps | $0.30/M | $1.20/M | — | — | 02/12/2026 | ||||
 Parasail | 197K | 0.4s | 118tps | $0.30/M | $1.20/M | — | — | 02/12/2026 | ||||
 DeepInfra | 197K | 0.5s | 45tps | $0.27/M | $0.95/M | Read:$0.03/M Write:— | — | — | 02/12/2026 | |||
 Amazon Bedrock | 1M | 0.7s | 71tps | $0.30/M | $1.20/M | — | — | 02/12/2026 | ||||
 Blackbox | 128K | 2.3s | 324tps | $0.07/M | $0.57/M | — | — | +1 | 02/12/2026 |