d-Matrix DEMO CLOUD

Experience inference on d-Matrix

Request access to the d-Matrix Demo Cloud and run leading AI models on purpose-built Corsair™ inference compute, including heterogeneous GPU + Corsair deployments.

  • High throughput
  • Low latency
  • Power efficient

What you’ll get access to:

Explore the models, APIs, tools and inference resources available in your Demo Cloud environment.

  1. Leading AI models

    Run popular open models including Llama, Qwen, Kimi, GLM and more.

  2. Corsair™ inference compute

    Experience d-Matrix purpose-built inference infrastructure designed for high throughput, low latency and power-efficient inference.

  3. OpenAI-compatible APIs

    Use familiar APIs and SDKs to connect your applications and existing workflows.

  4. Model catalog

    Explore available models, context lengths, data formats and deployment status.

  5. Developer tutorials

    Follow step-by-step examples to make API calls and test inference workloads.

  6. Your own API access

    Once approved, generate an inference API key directly in your Demo Cloud environment.

Request Demo Cloud Access

Complete the form to request access.
Tell us a bit about yourself and how you plan to use d-Matrix Demo Cloud. Our team will review your request and follow up with access details.