# Json format in Postman for Inference API

**URL:** <https://discuss.huggingface.co/t/json-format-in-postman-for-inference-api/9020>\
**Category:** Beginners\
**Created:** [August 6, 2021, 1:29pm UTC](https://discuss.huggingface.co/t/json-format-in-postman-for-inference-api/9020 "2021-08-06T13:29:33Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![JoeFr](https://avatars.discourse-cdn.com/v4/letter/j/f475e1/32.png) [@JoeFr](https://discuss.huggingface.co/u/JoeFr)\
**Post date:** [August 6, 2021, 1:29pm UTC](https://discuss.huggingface.co/t/json-format-in-postman-for-inference-api/9020/1 "2021-08-06T13:29:33Z")

</div>

Hello,

I’m just testing out some models using the Inference API. It works fine for all models which take a single input like text generation and question answering. But, I get errors for all models which need parameters like q&a and classification, saying:  
“error”: argument needs to be of type (SquadExample, dict)"

I tried:  
{  
“inputs”: “Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!”,  
“parameters”: {“candidate\_labels”: [“refund”, “legal”, “faq”]},  
}

as well as:

```
    sequence = "Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!"
    candidate_labels = ["refund", "legal", "faq"]

```

Thanks for your answer.

Best