# Configuring Open AI Compatible Endpoint

**URL:** <https://discourse.devontechnologies.com/t/configuring-open-ai-compatible-endpoint/86531>\
**Category:** Artificial Intelligence\
**Tags:** feature-request\
**Created:** [March 8, 2026, 4:10pm UTC](https://discourse.devontechnologies.com/t/configuring-open-ai-compatible-endpoint/86531 "2026-03-08T16:10:39Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![rkaplan](https://discourse.devontechnologies.com/letter_avatar_proxy/v4/letter/r/a3d4f5/32.png) [@rkaplan](https://discourse.devontechnologies.com/u/rkaplan)\
**Post date:** [March 8, 2026, 4:10pm UTC](https://discourse.devontechnologies.com/t/configuring-open-ai-compatible-endpoint/86531/1 "2026-03-08T16:10:39Z")

</div>

I am attempting to configure an OpenAI compatible endpoint but I am unable to enter the model name manually.

I understand from a prior post that DT4 needs to retreive the model list in order to determine model capability and that you look at a /v1/models endpoint.

In the case of cerebras.ai there is indeed a /v1/models endpoint but it requires authentication via the API key:

`https://api.cerebras.ai/v1/models`

Alternatively there is a public models endpoint that requires no authentication:

`https://api.cerebras.ai/public/v1/models`

Is it possible to support one of these /models endpoints? Or alternatively let the user configure the tools and other metadata at his own risk?

 ![image](https://devontech-discourse.s3.dualstack.us-east-1.amazonaws.com/uploads/original/3X/e/7/e7e295d5fcd54e99d7112e3fa3319502db6dc768.jpeg)

> [@DT4.1, support entry of AI Model manually in OpenAI (Compatible)](https://discourse.devontechnologies.com/t/dt4-1-support-entry-of-ai-model-manually-in-openai-compatible/85283):
>
> I am currently running an API server. However, it does not support automagical AI model detection. Can DT add the support of the entry of model name manually? Thanks!

---

<div class="post-metadata">

**Author:** ![BLUEFROG](https://discourse.devontechnologies.com/user_avatar/discourse.devontechnologies.com/bluefrog/32/135_2.png) [@BLUEFROG](https://discourse.devontechnologies.com/u/BLUEFROG)\
**Post date:** [March 8, 2026, 10:43pm UTC](https://discourse.devontechnologies.com/t/configuring-open-ai-compatible-endpoint/86531/2 "2026-03-08T22:43:39Z")

</div>

> I understand from a prior post that DT4 needs to retreive the model list in order to determine model capability and that you look at a /v1/models endpoint.

As mentioned many times, we can’t add support for every AI provider and aggregator that pops up online. People need to investigate _ **if** _ there’s an OpenAI compatible endpoint and what the correct URL is. You should be looking for chat completion endpoints. In this case, the actual endpoint appears to be `https://api.cerebras.ai/public/v1/chat/completions` but we logically can’t say what kind of access that really allows.

---

<div class="post-metadata">

**Author:** ![rkaplan](https://discourse.devontechnologies.com/letter_avatar_proxy/v4/letter/r/a3d4f5/32.png) [@rkaplan](https://discourse.devontechnologies.com/u/rkaplan)\
**Post date:** [March 9, 2026, 12:02am UTC](https://discourse.devontechnologies.com/t/configuring-open-ai-compatible-endpoint/86531/3 "2026-03-09T00:02:13Z")

</div>

> [@BLUEFROG](#):
>
> In this case, the actual endpoint appears to be `https://api.cerebras.ai/public/v1/chat/completions` but we logically can’t say what kind of access that really allows.

Hi @BLUEFROG

The endpoint In the image is indeed the working endpoint - I have it working in another app:

[https://api.cerebras.ai/v1](https://api.cerebras.ai/v1)

The issue as I understand it from the prior forum post is that DT4 looks for a “V1/models” endpoint to get metadata about the model. For Cerebras that endpoint is instead “/public/V1/models”

I totally understand you cannot support every model; that is why I suggested you could simply leave it to the user to configure the tools and other metadata if DT4 does not find the models endpoint.

While you cannot support “every model” I believe the performance advantage of Cerebras hardeware is profound - at a really low cost.

Typical performance I get in Devonthink on OpenRouter for most models is at best 50-60 tokens per second:

 ![image](https://devontech-discourse.s3.dualstack.us-east-1.amazonaws.com/uploads/original/3X/6/f/6fb015f25dc4f0fb5c8a2b32235a84d27efb42cd.png)

Typical performance I get in Devonthink on OpenRouter for gpt-oss-120b when OpenRouter is configured for best throughput is 300 tokens per second:

 ![image](https://devontech-discourse.s3.dualstack.us-east-1.amazonaws.com/uploads/original/3X/8/1/814e90a2da657f8d6259a41d095fc07d47b1691a.png)

Now that alone is frankly stunning - and it is really impressive when using Chat in Devonthink. This is an inexpensive model which yields a response about 5-6 times faster than typical models. Impressive.

But Devonthink does not let you specify a particular Openrouter provider other than generically “best throughput”. When I use my own app and either specify the Openrouter provider or directly access the Cerebrex API this is what I get:

 ![image](https://devontech-discourse.s3.dualstack.us-east-1.amazonaws.com/uploads/original/3X/f/1/f16045366ce88f4388b10bbfee6398bcf58f3ff8.png)

So that is an increase from 60 tokens per second for typical Devonthink models to over 2100 tokens per second. _ **35 times faster - real world.** _ Cost $0.35/M input, $0.75/M output. They advertise a theoretical 3000 tokens/second maximum - I am getting 2100 tokens per second real-world. In my custom app I am conversing with a 1,000 page PDF Chatbox and getting back sophisticated answers faster than I can read them.

I do not think this is a niche use case - the speed/cost are likely of interest to most who use AI in DT4, and I suspect the development work for DevonTech to implement Cerebras support would be trivial.

> **[Cerebras](https://www.cerebras.ai/pricing)**
>
> Cerebras is the go-to platform for fast and effortless AI training. Learn more at cerebras.ai.

---

<div class="post-metadata">

**Author:** ![cgrunenberg](https://discourse.devontechnologies.com/user_avatar/discourse.devontechnologies.com/cgrunenberg/32/7172_2.png) [@cgrunenberg](https://discourse.devontechnologies.com/u/cgrunenberg)\
**Post date:** [March 9, 2026, 6:29am UTC](https://discourse.devontechnologies.com/t/configuring-open-ai-compatible-endpoint/86531/4 "2026-03-09T06:29:10Z")

</div>

> [@rkaplan](#):
>
> The endpoint In the image is indeed the working endpoint - I have it working in another app:

DEVONthink expects the completions endpoint, not the APIs base URL.

---

<div class="post-metadata">

**Author:** ![rkaplan](https://discourse.devontechnologies.com/letter_avatar_proxy/v4/letter/r/a3d4f5/32.png) [@rkaplan](https://discourse.devontechnologies.com/u/rkaplan)\
**Post date:** [March 9, 2026, 12:56pm UTC](https://discourse.devontechnologies.com/t/configuring-open-ai-compatible-endpoint/86531/5 "2026-03-09T12:56:08Z")

</div>

> [@cgrunenberg](#):
>
> DEVONthink expects the completions endpoint, not the APIs base URL.

OK - simple solution 🙂. [@BLUEFROG was initially correct - I should have tried that earlier. Thank you both.]

Performance is beyond stunning - at minimal cost. Definitely something I would recommend other users try.

For documents within the 131K context window response is instant using DT4.

For documents or document sets beyond the context window size is there a way to still use DT4? I have used a custom app which combines Cerebras with Langchain Refine Chain - that allows context of almost any length via iteration.

 ![image](https://devontech-discourse.s3.dualstack.us-east-1.amazonaws.com/uploads/original/3X/b/4/b481bea0ee1268d781337629459f13135a751c9f.jpeg)

---

<div class="post-metadata">

**Author:** ![cgrunenberg](https://discourse.devontechnologies.com/user_avatar/discourse.devontechnologies.com/cgrunenberg/32/7172_2.png) [@cgrunenberg](https://discourse.devontechnologies.com/u/cgrunenberg)\
**Post date:** [March 9, 2026, 1:17pm UTC](https://discourse.devontechnologies.com/t/configuring-open-ai-compatible-endpoint/86531/6 "2026-03-09T13:17:47Z")

</div>

> [@rkaplan](#):
>
> For documents or document sets beyond the context window size is there a way to still use DT4?

Only by manually switching the provider/model.

---

<div class="post-metadata">

**Author:** ![rkaplan](https://discourse.devontechnologies.com/letter_avatar_proxy/v4/letter/r/a3d4f5/32.png) [@rkaplan](https://discourse.devontechnologies.com/u/rkaplan)\
**Post date:** [March 9, 2026, 1:37pm UTC](https://discourse.devontechnologies.com/t/configuring-open-ai-compatible-endpoint/86531/7 "2026-03-09T13:37:29Z")

</div>

> [@cgrunenberg](#):
>
> Only by manually switching the provider/model.

Well 131K context size is decent enough in many cases - definitely worth trying out. Super impressive performance of that Chat with this model - Cerebras hardware does indeed achieve thousands of tokens per second.