# Use DeepInfra as provider for Embedding Model **URL:** \ **Category:** Support\ **Created:** [September 30, 2025, 6:47pm UTC](https://forum.weaviate.io/t/use-deepinfra-as-provider-for-embedding-model/22008 "2025-09-30T18:47:20Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![alber70g](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/alber70g/32/7680_2.png) [@alber70g](https://forum.weaviate.io/u/alber70g)\ **Post date:** [September 30, 2025, 6:47pm UTC](https://forum.weaviate.io/t/use-deepinfra-as-provider-for-embedding-model/22008/1 "2025-09-30T18:47:20Z")
### How to use a OpenAI API Compatible embeddings endpoint? Currently there seems to be no way to add a custom OpenAI API Compatible endpoint. I want to use DeepInfra as they host Qwen3-embedding. How to do this? ---
**Author:** ![alber70g](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/alber70g/32/7680_2.png) [@alber70g](https://forum.weaviate.io/u/alber70g)\ **Post date:** [September 30, 2025, 7:28pm UTC](https://forum.weaviate.io/t/use-deepinfra-as-provider-for-embedding-model/22008/2 "2025-09-30T19:28:50Z")
Okay, this is terrible implementation detail. The base url is DeepInfra [https://api.deepinfra.com/v1/openai/embeddings](https://api.deepinfra.com/v1/openai/embeddings). With [https://webhook.site/](https://webhook.site/) i found out that weaviate just appends /v1/embeddings, like, for real this is an PR oversight I guess, cuz it’s unusable now. Either use the full url, or just add /embeddings, but adding the v1 is plain weird ---
**Author:** ![DudaNogueira](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dudanogueira/32/7846_2.png) [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)\ **Post date:** [September 30, 2025, 8:39pm UTC](https://forum.weaviate.io/t/use-deepinfra-as-provider-for-embedding-model/22008/3 "2025-09-30T20:39:10Z")
hi @alber70g ! the idea of `text2vec-openai` is to be closely tied with openai and openai only. Of course, we can always push it further 😜 I am afraid there isn’t a module that will allow you to take full control of the api endpoint 🤔 `text2vec-ollama` for example will append [`/api/embed`](https://webhook.site/cd5b7b89-12e4-4ba4-8481-6b73580406a4/api/embed) while `text2vec-azure` will append resource\_id, etc. I see some options from here: 1 - Open a GH Feature request to either allow pass “X-OpenAI-Basepath” or create DeepInfra’s own module 2 - Put something in between, like [LiteLLM](https://www.litellm.ai/), and handle this path issue. 3 - hardcode it on Weaviate code 😬 Let me know if this helps! THanks! ---
**Author:** ![alber70g](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/alber70g/32/7680_2.png) [@alber70g](https://forum.weaviate.io/u/alber70g)\ **Post date:** [October 1, 2025, 7:03am UTC](https://forum.weaviate.io/t/use-deepinfra-as-provider-for-embedding-model/22008/4 "2025-10-01T07:03:47Z")
I did something similar to 2 I have a caddy proxy setup that’ll proxy from [embeddings.mydomain.com/v1/embeddings](http://embeddings.mydomain.com/v1/embeddings) to [https://api.deepinfra.com/v1/openai/embeddings](https://api.deepinfra.com/v1/openai/embeddings) This seems to work. Note: it would be nice to have this behaviour of appending `/v1/embeddings` to the baseURL written down somewhere in the docs of configuring the tex2vec-openai so it’s at least visible. Now it was a black box that I only found out when using the webhook.site test ---
**Author:** ![DudaNogueira](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dudanogueira/32/7846_2.png) [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)\ **Post date:** [October 1, 2025, 1:37pm UTC](https://forum.weaviate.io/t/use-deepinfra-as-provider-for-embedding-model/22008/5 "2025-10-01T13:37:49Z")
Tip: Whenever you want to learn something directly from the codebase, you can ask here 😉 > **[weaviate/weaviate | DeepWiki](https://deepwiki.com/weaviate/weaviate)** > > Weaviate is an open-source, cloud-native vector database designed for efficient storage, search, and retrieval of data using vector embeddings. This page provides a technical summary of the Weaviate c ---
**Author:** ![alber70g](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/alber70g/32/7680_2.png) [@alber70g](https://forum.weaviate.io/u/alber70g)\ **Post date:** [October 3, 2025, 8:14am UTC](https://forum.weaviate.io/t/use-deepinfra-as-provider-for-embedding-model/22008/6 "2025-10-03T08:14:21Z")
Thank you! This _is_ a great resource