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
| Price | Standard |
|---|---|
| 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
| Workload | Input / output | Cache share | Estimated cost |
|---|---|---|---|
| Quick check | 10K / 1K × 1 | 0% | $0.00420 |
| Long analysis | 100K / 4K × 1 | 50% | $0.023 |
| Workday | 20K / 2K × 1,000 | 30% | $6.96 |
More from MiniMaxAll MiniMax models
| Model | Context | Input / M | Output / M | Intel. |
|---|---|---|---|---|
| MiniMax M2.7 | 205K | $0.250 | $1.00 | 38.1 |