Nex-N2.5-Max
MoE premierNex AGI’s open flagship: 1.6 trillion total parameters with 49 billion active per token, like a vast reference library where each question only pulls the shelf it needs (that is what the mixture of experts design buys you: huge stored knowledge, modest running cost). A 1.05M token context window means it reads an entire codebase or a day of transcribed meetings in one pass. The family scales down: Pro at 397B and mini at 35B, all open weights.
- 1600.0B
- 1050k
- Nex AGI
- Sep 2026
Save your hardware and every model page answers the real question: will it run on your machine, and how fast?
Join free - save your rig →Or run it in the cloud
No per-token API provider pricing tracked for Nex-N2.5-Max yet. For flagship list prices, see the calculator.
Inference cost over time
Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.