Skip to content

MiniMax M3

MiniMax M3 is MiniMax's first model with a 1M tokens context window and native multimodal input. It targets software engineering, terminal-based tool use, and agentic web browsing, with a max output of 1M tokens per request.

ReasoningTool UseVision (Image)File InputImplicit Caching
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'minimax/minimax-m3',
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
0.4s
221tps
$0.15/M$0.60/M
Read:$0.06/M
Write:$0.38/M
blackbox logo
fireworks logo
minimax logo
+2
03/18/2026
205K
1.5s
43tps
$0.60/M$2.40/M
Read:$0.06/M
Write:$0.38/M
+2
minimax logo
03/18/2026
1M
0.5s
326tps
$0.07/M$0.57/M
Read:$0.03/M
Write:$0.38/M
+1
bedrock logo
blackbox logo
deepinfra logo
+3
02/12/2026
205K
1.1s
41tps
$0.60/M$2.40/M
Read:$0.03/M
Write:$0.38/M
+1
minimax logo
novita logo
02/12/2026
205K
0.4s
333tps
$0.30/M$1.20/M
Read:$0.03/M
Write:$0.38/M
+1
bedrock logo
minimax logo
novita logo
10/27/2025
205K
0.7s
86tps
$0.30/M$1.20/M
Read:$0.03/M
Write:$0.38/M
+1
minimax logo
novita logo
10/27/2025