Minimax M3
Minimax M 3 is a native multimodal chat model developed by Minimax, capable of processing text and image inputs with a context window of 1,048,576 tokens. It excels in coding and cowork capabilities, achieving frontier-level performance across long-horizon agentic benchmarks, and notably features MiniMax Sparse Attention (MSA), a high-performance sparse attention operator designed for efficient processing of million-token contexts.
Input
Output
Context
1049K
Max Output
512K
Parameters
427B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Benchmarks
Estimated GPU Requirements for Minimax M3
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.