What path syntax does the mapping use?

Dot notation for object keys and bracket or dot for array indices: a.b.c, items[2].name, or items.2.name all work. Paths are read from the source and written into the target.

What happens if an old path is missing?

That mapping is skipped and listed under "unmatched" so you can see which source fields were absent. The rest of the migration still runs.

Can I create nested output structures?

Yes. Writing to a path like meta.usage.tokens or list.0.id automatically creates the intermediate objects and arrays in the output.

Is my data sent to a server?

No. The migration runs entirely in your browser using local JavaScript. Nothing you paste is uploaded or stored.

LLM Output Schema Migrator

Migrate LLM JSON between schema versions

When you change a prompt, swap models, or upgrade an API, the shape of the JSON your model returns often changes too — keys get renamed, nesting moves, arrays get wrapped. This tool lets you write a simple old-path → new-path mapping and reshape a pasted response into your target schema, so downstream code keeps working without manual editing.

How the mapping works

Each line of the mapping is a rule: read the value at the source path in the pasted JSON, then write it at the destination path in a brand-new output object. Paths use dot notation for object keys (message.content) and either bracket or dot notation for array indices (choices[0] or choices.0). Writing to a path that doesn’t exist yet creates the intermediate objects and arrays for you, so you can both flatten and re-nest in a single pass. Any source path that can’t be resolved is reported back as unmatched rather than silently failing.

Tips and examples

Renaming a top-level key: result -> data.
Pulling a nested value up: choices[0].message.content -> text.
Re-nesting flat fields: id -> record.id and name -> record.name.
Run the migrated output back through the tool with a second mapping to do a multi-step transformation when one pass isn’t enough.