> ## Documentation Index
> Fetch the complete documentation index at: https://developers.reflection.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Third-party providers

> Use Beam through cloud providers, hardware partners, and inference providers

Use Beam through a cloud provider, run it on partner hardware, or call it through an inference provider. To serve Beam on your own compute instead, see the [Deployment overview](/deployment-overview).

## Cloud providers

Beam is available on Amazon Web Services and Google Cloud. Microsoft Azure and Oracle support is coming soon.

<CardGroup cols={2}>
  <Card title="Amazon Web Services" icon="aws" iconType="brands" href="https://aws.amazon.com/sagemaker/ai/deploy/">
    Amazon SageMaker AI
  </Card>

  <Card title="Google Cloud" icon="google" iconType="brands" href="https://cloud.google.com/model-garden">
    Model Garden
  </Card>

  <Card title="Microsoft Azure" icon="microsoft" iconType="brands" href="https://azure.microsoft.com/en-us/products/ai-foundry/models/">
    Foundry Models <Badge color="yellow" size="sm">Coming soon</Badge>
  </Card>

  <Card title="Oracle" icon="cloud" href="https://www.oracle.com/artificial-intelligence/enterprise-ai/">
    OCI Enterprise AI <Badge color="yellow" size="sm">Coming soon</Badge>
  </Card>
</CardGroup>

## Hardware partners

<CardGroup cols={2}>
  <Card title="Dell Enterprise Hub" icon="server" href="https://dell.huggingface.co/">
    On-premises AI models and apps, by Hugging Face
  </Card>
</CardGroup>

Reflection developed its [Kubernetes serving solution](/serving-kubernetes) in partnership with Dell for on-premises deployments.

## Inference providers

<CardGroup cols={3}>
  <Card title="Nscale" href="https://www.nscale.com/services/ai-services#inference-endpoints" horizontal arrow />

  <Card title="Applied Compute" href="https://www.appliedcompute.com/inference" horizontal arrow />

  <Card title="Baseten" href="https://www.baseten.co/products/dedicated-inference/" horizontal arrow />

  <Card title="Cloudflare" href="https://www.cloudflare.com/products/workers-ai/" horizontal arrow />

  <Card title="CoreWeave" href="https://coreweave.com/products/coreweave-forge/dedicated-inference" horizontal arrow />

  <Card title="Databricks" href="https://www.databricks.com/product/model-serving" horizontal arrow />

  <Card title="Fireworks AI" href="https://fireworks.ai/inference" horizontal arrow />

  <Card title="Hermes" href="https://portal.nousresearch.com/models" horizontal arrow />

  <Card title="LM Studio" href="https://lmstudio.ai/developers" horizontal arrow />

  <Card title="Modal" href="https://modal.com/products/inference" horizontal arrow />

  <Card title="Nebius" href="https://nebius.com/services/token-factory/inference-service" horizontal arrow />

  <Card title="Ollama" href="https://ollama.com/" horizontal arrow />

  <Card title="OpenCode" href="https://opencode.ai/go" horizontal arrow />

  <Card title="OpenRouter" href="https://openrouter.ai/models" horizontal arrow />

  <Card title="Together AI" href="https://www.together.ai/serverless-inference" horizontal arrow />

  <Card title="Vercel" href="https://vercel.com/ai-gateway" horizontal arrow />

  <Card title="Weights & Biases" href="https://www.coreweave.com/products/coreweave-forge/serverless-inference" horizontal arrow />
</CardGroup>