MiniMax: MiniMax M3
minimax/minimax-m3
28th smartest of 182ReasoningToolsJSONVision
Intelligence
44.4
28th of 182
Design Elo
1284
Website
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.300
134th cheapest
Context
1.0M
512K max out
How it compares
Smarter than85%
of all ranked models
Cheaper than60%
of all ranked models
Overview
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis94th percentile
Intelligence Index
44.4
Coding Index
58.6
GPQA Diamond
93%
Humanity's Last Exam
37%
SciCode
45%
Tau²-Bench (agentic)
89%
Design Arena · Elo9,163 tournaments
Website
1284
3D
1280
Data Viz
1267
svg
1218
Providers & pricing (9)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| GMICloudfp8 | $0.240 | $0.960 | 1.0M | 99.6% |
| Novitafp8 | $0.300 | $1.20 | 1M | 99.8% |
| Venicefp8 | $0.300 | $1.20 | 524K | 90.5% |
| Minimaxfp8 | $0.300 | $1.20 | 524K | 99.6% |
| AtlasCloudfp8 | $0.300 | $1.20 | 524K | 99.9% |
| Together | $0.300 | $1.20 | 524K | 98.6% |
| Morph | $0.300 | $1.20 | 256K | 99.9% |
| DeepInfrafp8 | $0.300 | $1.20 | 524K | 99.7% |
| Parasailfp8 | $0.300 | $1.20 | 1.0M | 96.5% |
Specifications
Context window1.0M
Max output512K
Knowledge cutoff—
Input modalitiestext, image, video
Output modalitiestext
Prompt caching—
Cache read price$0.060/M
ModeratedNo
Open weightsMiniMaxAI/Minimax-M3 ↗
MiniMax M3 FAQ
How much does MiniMax M3 cost?
MiniMax M3 costs $0.300 per million input tokens and $1.20 per million output tokens via OpenRouter, making it 134th cheapest of 332 paid models.
How smart is MiniMax M3?
MiniMax M3 scores 44.4 on the Artificial Analysis Intelligence Index, ranking 28th of 182 benchmarked models, with a GPQA Diamond score of 93%.
What is MiniMax M3's context window?
MiniMax M3 supports a 1.0M-token context window and can output up to 512K tokens. It accepts text, image, video input.