Taurus Ethernet Smart Cable Modules™

Flexible, high-performance Active Electrical Cables for AI and cloud connectivity

Download Portfolio Brief

Unleashing High Density AI Connectivity

  • Extend 200/400/800G Ethernet signal reach for high-density AI racks using Active Electrical Cables
  • Enhance signal integrity and bandwidth utilization for diverse AI topologies with thin and flexible cables
  • Scalable across diverse systems using standard connector form factors with gearbox and breakout options
  • COSMOS suite for performance optimization and seamless fleet management across dense AI platforms

Taurus Highlights

Optimizing Ethernet Connectivity for AI and Cloud

Extended Robust
Signal Reach

Over copper cables

Flexible Copper
Cables

Optimizing routing, service, and airflow

Enhanced Diagnostics
& Telemetry

Advanced capabilities through out-of-band management

Why Use Taurus Ethernet Smart Cable Modules?

Taurus enables robust, easy-to-design 100G/Lane Ethernet connectivity with high reliability and maximum uptime, featuring the COSMOS’ built-in suite for advanced fleet management, security, and deep diagnostics.

Robustness

  • Extended Cable Line Rate

    Future proof scalability for 200G/400G/800G

  • Low Power

    Uses 50% less power than Active Optical Cables

  • Low Latency

    Low latency operation at <50ns

  • Security

    Advanced security features help prevent malicious attacks of unauthorized firmware loading, module diagnostics access, and configurations

Easy System Design

  • Thin Cable Gauge

    Up to 34AWG

  • Fewer Twinax Pairs

    8 pairs at 200G/400G/800G reduces overall external diameter of cables

  • Extended Reach

    Up to 7m of reach

  • Flexible Supply Chain

    Taurus Smart Cable Modules are compatible with multiple cable vendors for easy second sourcing of active cable assembly

Fleet Management

  • Quick Debug

    Self-test features enable rapid troubleshooting

  • Deep Diagnostics

    Cable-side and host-side diagnostics enable easy management of entire fleets

Use Cases

Switch-to-Server

Enabling an “Active” plus “Smart” approach to higher-bandwidth Switch-to-Server Ethernet interconnects and Switch-to-NIC bandwidth utilization

Resources

Ordering Information

Orderable Part NumberDescriptionMax Data GenCable Line RateModePackage / ConnectorOrdering
EM400-QDX400G QSFP-DD Taurus Smart Cable Module400G50G/Lane, 100G/LanePAM4QSFP-DDContact Us, https://www.asteralabs.com/product-details/em400-qdx/
EM400-EPS400G OSFP Taurus Smart Cable Module400G50G/Lane, 100G/LanePAM4OSFPContact Us, https://www.asteralabs.com/product-details/em400-eps/
EM800-EPS800G OSFP Taurus Smart Cable Module800G100G/LanePAM4OSFPContact Us, https://www.asteralabs.com/product-details/em800-eps/
EM800-QDX800G QSFP-DD Taurus Smart Cable Module800G100G/LanePAM4QSFP-DDContact Us, https://www.asteralabs.com/product-details/em800-qdx/
EM200-QDX200G QSFP-DD Taurus Smart Cable Module200G25G/LaneNRZQSFP-DDContact Us, https://www.asteralabs.com/product-details/em200-qdx/

Breaking the 100 GB/s Barrier: Astera Labs and Micron Demonstrate Production-Ready PCIe 6 Storage Performance at FMS 2025

The future of AI infrastructure arrived at the Future of Memory and Storage (FMS) 2025 conference, where Astera Labs and Micron achieved a groundbreaking milestone: over 100 GB/s of sustained throughput using production-ready PCIe 6 technology. This industry-first demonstration represents a transformative advancement in AI storage performance, featuring four Micron 9650 PCIe Gen6 SSDs and…

Read more

Astera Labs at FMS 2025: Accelerating Storage and Memory Innovation in the AI Infrastructure 2.0 Era

As AI models push computational boundaries with breakthrough reasoning capabilities, storage and memory must also evolve to optimize AI Infrastructure 2.0. From training massive models to enabling real-time inference, every part of the AI workflow relies on seamless connectivity between diverse storage and memory technologies.Join Astera Labs at the Future of Memory and Storage Summit…

Read more

Astera Labs at OCP APAC Summit: Advancing Open AI Infrastructure 2.0 Through Rack-Scale Connectivity

As AI training clusters scale to 200,000+ GPUs, traditional server architectures require a fundamental paradigm shift to handle this unprecedented scale. Join Astera Labs at the OCP APAC Summit, August 5-6 in Taipei, as we put a spotlight on the transition to AI Infrastructure 2.0—where the rack is replacing the server as the new unit of compute.This transformation isn’t just evolutionary—it’s…

Read more

Astera Labs Announces Third Quarter 2025 Financial Conference Participation

SAN JOSE, CA, U.S. – Aug. 20, 2025 – Astera Labs, Inc. (Nasdaq: ALAB), a leader in semiconductor-based connectivity solutions for rack-scale AI infrastructure, today announced its participation in financial conferences for the third quarter 2025.Deutsche Bank 2025 Technology Conference on Aug. 28, 2025. Astera Labs’ presentation is scheduled for 12:30 pm PT.Citi’s 2025 Global…

Read more

Astera Labs Announces Financial Results for the Second Quarter of Fiscal Year 2025

Record quarterly revenue of $191.9 million, up 20% QoQ and 150% YoY, and record operating cash flow generation of $135.4 millionIndustry leading PCIe 6 connectivity portfolio ramping in volume on customized rack-scale AI systemsScorpio Fabric Switch design wins expand across multiple new customers and applicationsSAN JOSE, CA, U.S. – August 5, 2025 – Astera Labs, Inc. (Nasdaq:…

Read more

Astera Labs Opens New Global Headquarters in San Jose to Accelerate AI Infrastructure Innovation

900-employee campus powers Astera Labs’ mission to usher in the rack-scale computing eraSAN JOSE, Calif.– July 18, 2025 – Astera Labs, Inc. (Nasdaq: ALAB), a provider of semiconductor connectivity solutions for AI and cloud infrastructure, today announced the opening of its new corporate headquarters in San Jose, California. Designed to accommodate up to 900 employees, the new…

Read more

Astera Labs Announces Conference Call to Review Second Quarter 2025 Financial Results

SAN JOSE, Calif., July 08, 2025 — Astera Labs, Inc. (Nasdaq: ALAB), a global leader in semiconductor-based connectivity solutions for AI and cloud infrastructure, today announced that it will release its financial results for the second quarter 2025 after the close of market on Tuesday, Aug. 5, 2025. Astera Labs will host a corresponding conference call at 1:30 p.m. Pacific Time, 4:30…

Read more

Leading the AI Infrastructure 2.0 Era

AI has outgrown the server. The rack is now the unit of compute — a tightly integrated, AI-optimized system. Welcome to AI Infrastructure 2.0.Astera Labs’ co-founders share how the company is leading the transition to AI Infrastructure 2.0 with a complete portfolio of purpose-built silicon hardware and software solutions grounded in open standards.

Read more

Accelerate AI with Real-World CXL Platforms

We collaborated with SMART Modular Technologies to showcase our Leo CXL™ Smart Memory Controller in a real-world setup that delivered up to 2TB of additional CXL memory with SMART CXL add-in cards.In the demo, Large Language Model inferencing tasks were run using FlexGen, achieving 5.5× higher throughput and 90% GPU utilization—demonstrating the efficiency gains CXL brings to AI workloads….

Read more

Boost AI with 100+ GB/s PCIe 6

Building on our successful DesignCon 2025 demonstration with Micron that achieved 54 GB/s with two SSDs, we’ve now scaled to four Micron 9650 PCIe Gen6 SSDs with three Scorpio P-Series Fabric Switches to achieve over 100 GB/s aggregate performance. This marks another step in expanding PCIe 6 adoption as Astera Labs continues to validate interoperability across an increasing range of endpoints,…

Read more