← Catalogsource ↗source ↗source ↗
MiniMax-M1-80k
AvailableMiniMaxFrontierOpen source
Open Apache-licensed hybrid-attention reasoning model with 456B total / 45.9B active parameters and a native 1M-token context.
Specifications
- License
- Open source · Apache-2.0
- Weights
- Downloadable
- Architecture
- hybrid
- Parameters
- 456B · 45.9B active
- Context window
- 1M tokens
- Max output
- 80K tokens
- Knowledge cutoff
- —
- Price (in / out, $/M)
- —
- Modalities
- TextCode
Benchmarks
GPQA Diamondself-reported
70%SWE-bench Verifiedself-reported
56%AIME 2025self-reported
76.9%Vendor-reported figures are claims until independently verified. See methodology.