Build advanced reasoning agents with MiniMax-M2.5, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers available completely free of charge, native tool calling support, open weights architecture. Access MiniMax-M2.5 via the MiniMax Coding Plan (minimax.io) API with up to 131K output tokens.
Tokens
Tokens
Tokens
MiniMax-M2.5 by MiniMax Coding Plan (minimax.io) costs Free per 1M input tokens and Free per 1M output tokens. Cached reads cost Free per 1M tokens. Cache writes cost Free per 1M tokens.