Fix malformed LLM JSON and validate it

Created by

Kadev Code

Actor

LLM JSON Repair & Schema Validator

Repair broken JSON from ChatGPT, Claude or Gemini outputs (single quotes, trailing commas, code fences, unquoted keys) and validate it against your JSON Schema. Pay only for valid, lossless results.

Try for free

LLM JSON Repair & Schema Validatorkadev-code/llm-json-repair

Index

Valid

Repaired JSON

Error

+4 fields

Input

Texts to repair(required):```json { name: 'Alice', "role": 'Engineer', "skills": ['Python', 'AI',], "active": True, } ``` Hope this helps!+1

Optional JSON Schema:{3 fields}

Extraction Mode:first

Fail on Error:false

Output fields

Index

Valid

Repaired JSON

Error

Issues detected

Loss risk

Warnings

Schema errors

How it works

Sign up on Apify or log in

The LLM JSON Repair & Schema Validator Actor is ready to run with the inputs already set for "Fix malformed LLM JSON and validate it". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Fix malformed LLM JSON and validate it" task

The LLM JSON Repair & Schema Validator Actor will start running based on the input automatically. You can also change all the input fields, like texts to repair, optional json schema, and more, to match your specific use case.

Receive the "Fix malformed LLM JSON and validate it" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as index, valid, repaired json, and more.

Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "Fix malformed LLM JSON and validate it" task via API.