Model specification · MiniMax

MiniMax M3

minimax/minimax-m3

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,...

SpecificationsReported values
Context window
1.0M
Maximum output
512K
Architecture
text+image+video->text
Tokenizer
Other
Knowledge cutoff
Moderated
No
Input modalities
text image video
Output modalities
text
Full pricingUSD where reported
PriceStandard
Input$0.300 / M
Output$1.20 / M
Benchmark indexesReported indexes
Intelligence
44.4
Coding
58.6
Agentic
35.4
Design Arena Elo
1238
Example workload costsStandard pricing only
WorkloadInput / outputCache shareEstimated cost
Quick check10K / 1K × 10%$0.00420
Long analysis100K / 4K × 150%$0.023
Workday20K / 2K × 1,00030%$6.96
More from MiniMaxAll MiniMax models
ModelContextInput / MOutput / MIntel.
MiniMax M2.7205K$0.250$1.0038.1