Blaxel is a cloud infrastructure built for AI agents. Our computing platform gives AI Builders the services, infra, and developer experience optimized to build and deploy agentic AI — with a twist: your agents can also take the wheel.
An AI agent is any application that leverages generative AI models to take autonomous actions in the real world—whether by interacting with humans or using APIs to read and write data.
This portal provides comprehensive documentation and API, SDK and CLI reference to help you operate Blaxel Platform.

​
Essential concepts

Blaxel is a cloud designed for agentic AI. It doesn’t force you into any kind of workflow or shaped box. While we encourage you to exploit architecture designs that we consider are more reliable, our toolkit gives you all the pieces you need to build agentic systems exactly the way you want. Blaxel consists of modular services that are engineered to work seamlessly together — but you can also just use any one of them independently. Think of it as a purpose-built set of building blocks that you can use to power and ship agents.

​
The building blocks

At the heart of Blaxel is our flagship Agents Hosting service. Agents Hosting lets you deploy your AI agents as serverless auto scalable endpoints.
  • Completely framework agnostic. Just bring your code, Blaxel builds it and runs it for you.
  • Asynchronous endpoints with automatic queuing and retries
  • Full observability — out-of-the-box
The rest of Blaxel’s cloud services include:
  • MCP Servers Hosting - Deploy custom tool servers on a fast-starting infrastructure to extend your agents’ capabilities.
  • Model Gateway - Intelligent routing layer to LLM providers with built-in telemetry, token cost control, and fallbacks capabilities
  • Sandboxes - Near instant-starting micro VMs that provide agents with their own compute runtime to execute code or run commands.
  • Batch Jobs - Scalable compute engine designed for agents to schedule and execute many AI processing tasks in parallel in the background

​
The Blaxel method

As the ultimate AI builder’s playground, Blaxel doesn’t require you to learn and adopt a framework or architecture. However, we do recommend best-practices from our experience working with top AI teams and aim to provide guardrails and framing when you build your agents.
  • Break down and distribute your agents whenever possible. A single monolithic agent handling all tool calls, LLM calls, and task workflows can be deployed to Blaxel—but it will be harder to maintain, monitor, and will use resources inefficiently. Blaxel SDK allows builders to split services and connect them from your code.
  • You can call LLM providers directly from your code, but we recommend you go through Blaxel’s Model Gateway for telemetry.
  • Similarly, while direct tool calls are possible, deploying separate MCP servers improves reusability, optimizes resources, and simplifies monitoring. Blaxel also optimizes placement globally when your serverless tool server needs to make multiple backend calls.
  • Break large agents into smaller, specialized sub-agents when possible—they’re easier to debug and observe.
  • Agentic systems naturally connect with many services both inside and outside your network, mixing North-South and East-West traffic in cloud terms. Strong observability is essential for reliability.
  • Reliability is the biggest challenge in agentic AI. Focus on fine-tuning your prompts, tool calls, data access, and orchestration logic—Blaxel will handle the execution.

​
A cloud built for agents

Agents will transform how we work in the coming years. Traditional cloud providers weren’t designed to handle them and their one-size-fits-all architecture holds them back. We built Blaxel to fix that. Blaxel is a cloud where AI agents themselves are the primary users. All products are accessible through MCP servers, allowing agents to create and manage resources via tool calls. Blaxel provides agents with all the compute they need to scale and perform optimally: products like Sandboxes give them their own dedicated personal computer(s) / computing environments, while Batch Jobs enable them to schedule background tasks at scale.

​
Which component should I use?

When building your agentic system, you’ll need to make architecture design choices. Blaxel offers several compute options, summarized below in order of latency performance:
  • Sandboxes: Perfect for maximum workload flexibility. These micro VMs provide full access to filesystem, network, and processes, booting from hibernation in under 25ms.
  • Agents Hosting (sync mode): Ideal for running HTTP API services that process requests within a few seconds.
  • Agents Hosting (async mode): Best for running HTTP API services handling longer requests without maintaining an open connection.
  • Batch Jobs: Designed for asynchronous tasks that may run for extended periods where boot latency is less critical. These jobs are triggered by providing specific input parameters, unlike Agents that are a fully hosted API.
ProductTypical useTypical workload durationBoot timeInput type
Agents Hosting (sync mode)Agent API that answers fasta few seconds (maximum 100 s)~2-4sCustom API endpoints
Agents Hosting (async mode)Agent API that processes data for a whilea few minutes (maximum 10 mins)~5sCustom API endpoints
Batch JobsSub-tasks scheduled in an agentic workflowminutes to hours (maximum 24 h)~30sSpecific input parameters
SandboxesGiving an agent its own compute runtimeseconds to hours~25msFully custom
MCP Servers HostingRunning an MCP server APIseconds to minutes (maximum 15 mins)~2-4sAPI following MCP

​
The Blaxel powerhouse

When you deploy workloads to Blaxel, they run on a technical backbone called the Global Agentics Network. Its natively serverless architecture automatically scales computing resources without any server management on your part. Global Agentics Network serves as the powerhouse for the entire Blaxel platform, from Agents Hosting to Sandboxes. It is natively distributed in order to optimize for low-latency or other strategies. It allows for multi-region deployment, enabling AI workloads (such as an AI agent processing inference requests) to run across multiple geographic areas or cloud providers. This is accomplished by decoupling this execution layer from a data layer made of a smart distributed network that federates all those execution locations. Finally, the platform implements advanced security measures, including fine-grained authentication and authorization through Blaxel IAM, ensuring that your AI infrastructure remains protected. It can be interacted with through various methods, including APIs, CLI, web console, and MCP servers.

​
Documentation structure

You might want to start with any of the following articles:
  • Get started: Deploy your first workload on Blaxel in just 3 minutes.
  • Product Documentation
    • Agents Hosting: Build and run AI agents that can scale.
    • MCP Servers Hosting: Expose capabilities and execute tool calls for your AI agents.
    • Model APIs: Learn about supported model types.
    • Sandboxes: Equip your agents with blazing-fast virtual machines to run commands and code.
    • Batch jobs: Scheduled jobs of batch processing tasks for your AI workflows.
    • Integrations: Discover how Blaxel works with other tools, frameworks, and platforms.
    • Observability: Monitor logs, traces and metrics for your agent runs.
    • Policies Governance: Manage your AI deployment strategies.
    • Security: Implement robust security measures for your AI infrastructure.
  • API reference: Comprehensive guide to Blaxel’s APIs.
  • CLI reference: Learn how to use Blaxel’s command-line interface.