Why Ingram Cloud

Less infrastructure between your code and your models.

Connect model providers, track spend, and run tools through one platform. Use the API for integration and the console for configuration, usage, and debugging.

Integrate once across model providers

Call OpenAI, Anthropic, and Gemini with an OpenAI-compatible client. Select the model on each request instead of maintaining a separate integration for every provider.

Use managed access or your own provider keys. Ingram Cloud resolves the credentials and records model usage against your project and user.

See the API contract

Centralize credentials, costs, and logs

Manage provider keys, model usage, budgets, and run history in the same console. Investigate a request alongside the cost it incurred.

With managed access, model charges and the platform fee use your Ingram Cloud balance. With your own keys, providers bill you directly; Ingram Cloud bills its platform fee and storage.

Explore usage controls

Use a hosted runtime when you need tools and state

Connect MCP tools, persist conversations, and attach a knowledge base. The platform runs the model-and-tool loop and stores the execution record.

You own your application code and any custom tools you host. Ingram Cloud handles tool orchestration, memory, credential refresh, and approval pauses.

Explore the runtime

Keep application controls in your code

Configure the platform through the API or Pulumi. Use scoped credentials and separate projects for your applications and environments.

The console uses the same public API. Webhooks deliver run and approval events to your application, so you can build your own operational workflows.

Configure with Pulumi

Connect your application.

Create a project, get a token, and follow the quickstart for your first API request.