# "Unsupported data type" when calling embedding API for o3-mini

**URL:** <https://community.openai.com/t/unsupported-data-type-when-calling-embedding-api-for-o3-mini/1252241>\
**Category:** API\
**Tags:** api\
**Created:** [May 5, 2025, 1:26pm UTC](https://community.openai.com/t/unsupported-data-type-when-calling-embedding-api-for-o3-mini/1252241 "2025-05-05T13:26:50Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![lkps](https://avatars.discourse-cdn.com/v4/letter/l/34f0e0/32.png) [@lkps](https://community.openai.com/u/lkps)\
**Post date:** [May 5, 2025, 1:26pm UTC](https://community.openai.com/t/unsupported-data-type-when-calling-embedding-api-for-o3-mini/1252241/1 "2025-05-05T13:26:51Z")

</div>

I’m trying to use the embeddings API via Azure AI Foundry. It’s returning the following error:

```auto
Traceback (most recent call last):
  File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File ".../ __main__.py", line 14, in <module>
    result = azure.embeddings.create(
  File ".../.venv/lib/python3.10/site-packages/openai/resources/embeddings.py", line 128, in create
    return self._post(
  File ".../.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1239, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
  File ".../.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1034, in request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Unsupported data type

```

### To Reproduce

```python
from openai import AzureOpenAI

LLM_ENDPOINT = "https://xxx.openai.azure.com/openai/deployments/o3-mini/chat/completions?api-version=2025-02-01-preview"
LLM_API_VERSION = "2025-02-01-preview"
LLM_API_KEY = "..."

azure = AzureOpenAI(
    azure_endpoint=LLM_ENDPOINT,
    api_key=LLM_API_KEY,
    api_version=LLM_API_VERSION,
)

result = azure.embeddings.create(
    model="o3-mini",
    input="test",
    encoding_format="float",
)

```

### OS

pop\_os 22.04

### Python version

Python v3.10

### Library version

openai v1.76.2

---

<div class="post-metadata">

**Author:** ![bgel](https://avatars.discourse-cdn.com/v4/letter/b/b5a626/32.png) [@bgel](https://community.openai.com/u/bgel)\
**Post date:** [May 13, 2025, 3:01pm UTC](https://community.openai.com/t/unsupported-data-type-when-calling-embedding-api-for-o3-mini/1252241/2 "2025-05-13T15:01:10Z")

</div>

I think you are using the wrong model. o3-mini is not an embedding model. The embedding models can be viewed at [https://platform.openai.com/docs/guides/embeddings](https://platform.openai.com/docs/guides/embeddings)

`text-embedding-3-small` and `text-embedding-3-large` , our newest and most performant embedding models, are now available. They feature lower costs, higher multilingual performance, and new parameters to control the overall size.`