High-speed model, suitable for real-time dialogues.

Small model, suitable for lightweight tasks.

Supports medium-length dialogues, applicable to various application scenarios.

Balances performance and cost, suitable for general scenarios.

Equipped with ultra-long context processing capabilities, especially suitable for long document analysis.

Supports large-scale context interactions, suitable for complex dialogue scenarios.

A high-speed large model based on the next-generation self-developed Attention architecture MFA, achieving results similar to step-1 at a very low cost, while maintaining higher throughput and faster response times. It is capable of handling general tasks and has specialized skills in coding.

step-2-16k-exp.description

A small visual model suitable for basic text and image tasks.

Supports visual input, enhancing multimodal interaction experiences.

This model possesses powerful image understanding capabilities. Compared to the step-1v series models, it offers enhanced visual performance.

This model has powerful video understanding capabilities.