Minimax VL 01
Minimax builds the Minimax VL 01, a chat model that excels at multimodal tasks, particularly visual question answering, as evidenced by its top performance on the ChartQA and DocVQA benchmarks. The model's architecture combines a Vision Transformer for visual encoding, a two-layer MLP projector for image adaptation, and a large language model, with a notable dynamic resolution feature that resizes input images to various resolutions for more accurate representation.
Input
Output
Context
8K
Max Output
-
Parameters
456.4B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Resources & Links
Estimated GPU Requirements for Minimax VL 01
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 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.