# \[text classification\] different result format for inference API and inference endpoint

**URL:** <https://discuss.huggingface.co/t/text-classification-different-result-format-for-inference-api-and-inference-endpoint/59767>\
**Category:** Intermediate\
**Created:** [October 25, 2023, 1:28am UTC](https://discuss.huggingface.co/t/text-classification-different-result-format-for-inference-api-and-inference-endpoint/59767 "2023-10-25T01:28:41Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ryansingman](https://avatars.discourse-cdn.com/v4/letter/r/43a26b/32.png) [@ryansingman](https://discuss.huggingface.co/u/ryansingman)\
**Post date:** [October 25, 2023, 1:28am UTC](https://discuss.huggingface.co/t/text-classification-different-result-format-for-inference-api-and-inference-endpoint/59767/1 "2023-10-25T01:28:42Z")

</div>

Hi all!

I am trying to deploy an inference endpoint for the [DeBERTa Base MNLI](https://huggingface.co/microsoft/deberta-base-mnli) model. While the endpoint deploys successfully, I am finding that the result format is different the free inference API as opposed to querying the inference endpoint. See the below results:

Inference endpoint:

```auto
>>> requests.post("<MY INFERENCE ENDPOINT>", headers={"Authorization": f"Bearer <HF API KEY>"}, json={"inputs": "[CLS] I love you. [SEP] I like you. [SEP]"}).json()
[{'label': 'ENTAILMENT', 'score': 0.9248048663139343}]

```

Inference API:

```auto
>>> requests.post("https://api-inference.huggingface.co/models/microsoft/deberta-base-mnli", headers={"Authorization": f"Bearer <HF API KEY>"}, json={"inputs": "[CLS] I love you. [SEP] I like you. [SEP]"}).json()
[[{'label': 'ENTAILMENT', 'score': 0.9248047471046448}, {'label': 'NEUTRAL', 'score': 0.07485755532979965}, {'label': 'CONTRADICTION', 'score': 0.00033764145337045193}]]

```

Note that through the inference API, I receive `ENTAILMENT`, `NEUTRAL`, and `CONTRADICTION` scores, where as with the inference endpoint, I only receive `ENTAILMENT`. For my application, I need all three scores.

It’s not immediately clear to me what’s going on here. When creating the inference endpoint, I did so by clicking the deploy dropdown on the `deberta-base-mnli` page, so I would expect for the deployed model to yield the same result format. I am able to replicate this when creating both CPU and GPU inference endpoints for the `deberta-base-mnli` model and when creating an inference endpoint for the `deberta-large-mnli` model.

Thanks in advance for the help!