Reasoning Models

Our reasoning models are built for deep analytical tasks, excelling at logical reasoning, math, and coding.

Step 3.5 Flash

step-3.5-flash is our flagship reasoning model, engineered for high-complexity tasks requiring deep logic and rapid execution. It excels at decomposing multi-step problems, executing tool calls, and maintaining coherence across massive datasets. It is the primary choice for complex workloads such as long-context agents, advanced software engineering, and comprehensive research automation.

• Mixture of Experts Architecture (MoE): Combines a massive 196B parameter knowledge base with high-efficiency inference (activating around 11B parameters per token). This delivers the logic depth of ultra-large models with the low latency of lightweight models.
• 256K Long Context: Maintains logical consistency when processing massive datasets or long documents.
• Native Agent Capabilities: Orchestrates precise tool calling and multi-step reasoning, which makes it ideal for agents and automation.
• Extreme Efficiency: Optimized for high throughput and cost-effective deployment without compromising reasoning quality.

Quick Start