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/

Addressing Connectivity Bottlenecks at Rack-Scale

As AI clusters scale from single nodes to thousand-GPU fabrics, connectivity is becoming the bottleneck that prevents all that compute from reaching its potential. NVIDIA’s Blackwell and Vera Rubin architectures have fundamentally redefined what a rack can do—but that density creates new challenges at every layer: scale-up, scale-out, memory, and storage. When any one of them lags, you’re… Read more

Why Connectivity is the New Frontier of AI Infrastructure—and What NVLink Fusion Means for the Future

Every year at GTC, the conversations on the show floor and in the hallways tell you something that raw specs alone can’t. This year, what I’m hearing is a clear inflection: the era of one-size-fits-all compute is over. Hyperscalers are deploying heterogeneous racks where NVIDIA GPUs sit alongside custom accelerators, XPUs, and purpose-built silicon developed for specific workload profiles—and… Read more

Inference Tokenomics: How CXL Memory Expansion Improves AI Economics

In our last post on Breaking Through the Memory Wall, we explored how CXL memory expansion addresses fundamental constraints in RAG and KV cache management. We expand on how inference application deployment has transitioned to a distributed architecture to address the requirements of large-scale applications, and how CXL-attached memory helps improve capacity and performance while lowering… Read more

Astera Labs Reports Fourth Quarter and Full Year 2025 Financial Results

Record quarterly revenue of $270.6 million, up 17% QoQ, and record full-year revenue of $852.5 million, up 115% year-over-yearBroadening Scorpio X-Series smart fabric roadmap to address expanding scale-up market opportunities supporting multiple customers, starting production ramp for lead platformAppointed Desmond Lynch as Chief Financial Officer with Mike Tate transitioning to the… Read more

Astera Labs Expands Global Footprint with New Israel Design Center to Support Growing Demand for AI Connectivity Solutions

New design center to focus on cutting-edge AI fabrics and emerging AI inference technologiesIndustry veteran Guy Azrad to lead operations as general manager of Astera Labs IsraelSAN JOSE, Calif. and TEL AVIV, Israel—Feb. 9, 2026—Astera Labs, Inc. (Nasdaq: ALAB), a leader in semiconductor-based connectivity solutions for rack-scale AI infrastructure, today announced a significant… Read more

Astera Labs Broadens Scorpio X-Series Smart Fabric Switch Roadmap to Address Expanding Scale-Up Market Opportunities

Scorpio X-Series Begins Initial Production with Merchant Scale-Up Switching Market Estimated to Reach $20 billion by 2030 [1]News Highlights:Developed in collaboration with hyperscalers, Scorpio X-series products are purpose-built to support scale-up networking, and are now shipping in initial production volumesExpanded features will include support for increased radix, platform-specific… Read more

Astera Labs Expands Connectivity Portfolio with Custom Solutions

NVLink Fusion-based custom solutions will be offered to support next-generation heterogenous AI infrastructureSAN JOSE, Calif.—Dec. 2, 2025—Astera Labs, Inc. (Nasdaq: ALAB), a leader in semiconductor-based connectivity solutions for rack-scale AI infrastructure, today announced plans to deliver custom connectivity solutions, a new offering designed to address the increasing complexity… Read more

Extending Reach of Scale-out Networks for AI Clusters

See our latest demo where our Scorpio P-Series Fabric Switches connect NVIDIA H200 GPUs and ConnectX-8 NICs – running real NCCL-based training workloads at max data rates. Our Taurus Ethernet-enabled AECs then extend reach up to 7m with full interoperability with NVIDIA Spectrum-X for switch-to-switch and ConnectX-8 for switch-to-NIC connectivity at 800G per linkLearn how this demo delivers:✅… Read more

How We Test – Taurus Interop

Learn how we conduct rigorous interop testing of Taurus Ethernet Smart Cable Modules with a range of hosts, NICs, and switches to ensure seamless deployment and minimize risk. Read more

Aries 6 Smart Cable Module Demo

In this demo video, see how Aries PCIe 6 Smart Cable Modules (SCMs) enable reliable, rack-to-rack PCIe 6 connectivity for AI scale-up infrastructure. Powered by Astera Labs’ COSMOS software suite and Scorpio Fabric Switches, the test platform demonstrates real-time link testing, monitoring, and debugging across four x16 active electrical cables. Learn how Aries 6 SCMs extend reach up to… Read more