The best open-weight, self-hostable alternatives to Mistral Large 2407 in 2026 — compared on price, context window and capabilities. Run them locally and cut API costs.
Refreshed from live data · olud.ai
Mistral Large 2407 is a proprietary, API-only model. These open-weight models can be self-hosted, run offline and used at a fraction of the cost — here's how the top ones stack up.
Within 0.6 pts of Mistral Large 2407 on the Artificial Analysis intelligence index · 60.0× cheaper per million output tokens
Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...
Granite 4.1 8B vs Mistral Large 2407 →Live ranking of open-weight models with pricing, context windows and capabilities.
Open the leaderboard →