Start building

Run your first wrapper-code AI workflow.

Start with a pre-built wrapper code instead of a blank prompt. Pass basic fields or files, run your selected model, and download the generated artifact.

Get an API key Open playground

Recommended start path

Pick a real use case first, then copy the wrapper-code API request.

Create or reuse an API key

Choose a wrapper from 125K+ options

Download the generated artifact

Quickstart

Four pieces turn a wrapper code into a production run.

Create an API key

Authenticate with x-api-key or Bearer zw_live_... from your dashboard.

Choose wrapper codes

Call reusable prompt behavior by code instead of writing prompts from scratch.

Pass basic inputs

Send variables, plain text, or uploaded files as context for the selected wrapper.

Track the ledger

Every execution records model, tokens, cost, artifact, billing source, and trace ID.

Examples

Use one API for wrapper codes, files, and async execution.

These examples show the wrapper-code V2 contract. Keep idempotency keys unique per operation to avoid duplicate executions.

curl -X POST https://api.zywrap.com/v2/runs \
  -H "x-api-key: $ZYWRAP_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: first-run-001" \
  -d '{
    "model": "openai-gpt-4o-mini",
    "input": {
      "text": "Summarize this product idea in three bullets."
    },
    "output": {
      "format": "markdown",
      "artifact": true
    }
  }'

Developer workflow

Prefer discovery first? Use the V2 playground.

Choose a category, use case, wrapper variation, model, file inputs, and overrides. Then run sync or async and download the artifact.

Open playground