Blitflow

Overview

Build and run Blitflow workflows from code — HTTP API, TypeScript SDK, and MCP server.

Blitflow runs AI workflows: graphs of nodes (image models, LLMs, media utilities) that turn inputs into generated outputs. You can design workflows visually in the Studio editor, or build them dynamically in code — and run either kind programmatically.

Three ways in, one contract

Every operation is defined once in the Blitflow API contract. The HTTP API, the TypeScript SDK, and the MCP server are all derived from the same contract, so they expose the same five operations with identical inputs and outputs:

OperationHTTPSDKMCP tool
nodes.listGET /v1/nodessearchNodes(client, …)nodes_list
nodes.getGET /v1/nodes/:idgetNode(client, id)nodes_get
runs.createPOST /v1/runsrun(…) / startRun(…)runs_create
workflows.getGET /v1/workflows/:idgetWorkflow(client, ref)workflows_get
runs.nodePOST /v1/runs/nodeclient.ops["runs.node"](…)runs_node

Pick the surface that fits:

SurfaceYou are…Reach for it when
HTTP APIany language, any runtimeyou want plain REST + SSE with a bearer token
SDK (@blitflow/sdk)a TypeScript appyou're building a product on top of Blitflow
MCPan AI agent / assistant (Claude, Cursor)you want a model to call Blitflow as a tool
CLI (blitflow)a person in a terminal / CIyou're scripting or experimenting

Prefer learning by task? The Guides show the same task on every surface, side by side.

Two ways to get a workflow

  1. Reference a published workflow. Design it in the Studio editor, publish a version, and run it by reference — <workflowId>@<version> such as abc123@2.1.0 or abc123@latest. See Versioning.
  2. Send an inline definition. Build the workflow JSON in code (by hand or with the SDK builder) and pass it directly to a run — no publishing step required.

Where to start

For AI agents

These docs are machine-readable: append .md to any page URL for clean Markdown, or fetch /llms.txt (an index of every page) and /llms-full.txt (the full text of all pages).

On this page