# Json format in Postman for Inference API

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fjson-format-in-postman-for-inference-api%2F9020%3E%5C
**Category:** Beginners\
**Created:** [August 6, 2021, 1:29pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fjson-format-in-postman-for-inference-api%2F9020 "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](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJoeFr)%5C
**Post date:** [August 6, 2021, 1:29pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fjson-format-in-postman-for-inference-api%2F9020%2F1 "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
