Serving models on OpenAI is harder than it should be

MLOps2 posts from 2 people2d active+00 posts in the last 7 days, 1 the 7 days before (fading)Unverified

Posts per day2 posts, Sep 18 to Oct 21

The posts behind it

2, newest first

GitHub issuesOct 9 [Feature]: Support OpenAI Decisions API as an auto-router classifier backend...as a provider - calling `{api_base}/v1/decisions`. However, there is currently **no way to use the OpenAI Decisions API as the auto-router's classifier backend**. ### Current state The auto-router's `classifier_type` supports: PR #45200 introduces `classifier_type:...BerriAI/litellm · elvis-cai1 reactionsOpen ↗GitHub issuesSep 18 [FR] Add STACKIT Model Serving as a native AI Gateway provider...Serving directly discoverable when configuring LLM endpoints. > #### Why is it currently difficult to achieve this use case? STACKIT AI Model Serving is OpenAI-compatible, so users can potentially work around the lack of a dedicated provider by configuring it through an existing...mlflow/mlflow · haya-fatima1 repliesOpen ↗

Companies and products named

Named2 posts

OpenAI Named1 post

MLflow Named1 post

Databricks Named1 post

Cloudflare

About this problem

Evidence

2 posts from 2 people in 2 places, about 1 a week over 22 days. Mostly on mlflow/mlflow, BerriAI/litellm. Tools named alongside: MLflow, Databricks, Cloudflare.

Frustration Frustration 0 of 3· Seen on GitHub issues

How it was grouped

Posts that state a pain and match the "model-serving" rule about OpenAI. First post Sep 18, 2026, latest Oct 9, 2026. Unverified: fewer than 3 posts, or one person or place only. Method

The same problem elsewhere

Elsewhere15 postsDeploying and serving models is harder than training Elsewhere9 postsServing models on MLflow is harder than it should be Elsewhere4 postsServing models on Ollama is harder than it should be Elsewhere2 postsServing models on ChatGPT is harder than it should be

Other OpenAI problems

Same product3 postsFine-tuning OpenAI is costly and unpredictable Same product50 postsOpenAI users keep asking for help Same product8 postsRunning OpenAI locally hits memory and speed limits Same product15 postsOpenAI upgrades break working setups Same product9 postsTrouble with OpenAI chat Same product7 postsTrouble with OpenAI responses Same product5 postsOpenAI fails to return valid structured output Same product5 postsTrouble with OpenAI astra Same product4 postsTrouble with OpenAI custom Same product4 postsTrouble with OpenAI image Same product3 postsOpenAI tables suffer from small files and skew Same product3 postsTrouble with OpenAI crashes

History

MomentumOct 16, 2026steady to fading

AddedOct 11, 2026Serving models on OpenAI is harder than it should be (2 posts)