Langflow: where a deprecated OpenAI model name lives

Where the model id lives

The Language Model page says the core component parameters include provider and model_name. It says the options depend on the selected provider and your global Models configuration. You enable models under your profile, Settings, Model Providers. Text models are listed under Language Models.

The OpenAI bundle page says the OpenAI component parameter model is the name of the OpenAI model to use. The description says options include gpt-3.5-turbo and gpt-4. That is the list printed on the page, not a claim that those are the only ids the field accepts.

The OpenAI Embeddings component on the same page has its own Model parameter. The page says its default is text-embedding-3-small. That field is the embedding model, not the chat model.

The credential is the API key in Model Providers, or the OpenAI component's API key parameter. This page does not show a key.

Sources: Langflow Language Model , Langflow OpenAI bundle , checked October 25, 2026.

How to pin or swap it

Pinning is selecting one model_name, or one model value, instead of leaving a template on the example ids the OpenAI page prints. To swap a shutdown, select the official replacement from the table and enable that model in Model Providers. The Language Model page says a model that is not enabled does not appear for selection.

An Agent can use its built-in model, or a Language Model component whose output type is Language Model. The Language Model page says the Agent then inherits the connected component's model. Change the component, not only a label on the Agent, when the connected model is the one that is shutting down.

Neither page documents a fallback list or a router alias.

Sources: Langflow Language Model , Langflow OpenAI bundle , checked October 25, 2026.

GPT-6 function tools

The Language Model page and the OpenAI bundle page do not document a Responses API switch. This page does not add one.

If the name you select is an OpenAI chat id, OpenAI's Using GPT-6 guide still says GPT-6 Astra and GPT-6.1 Sol tool calling requires the Responses API, and GPT-6 Sol and GPT-6 Luna accept function tools on Chat Completions only with reasoning effort none. Read the error pages before you send tools through a component that is still on Chat Completions.

Sources: Langflow Language Model , Langflow OpenAI bundle , Using GPT-6 , checked October 25, 2026.

Upcoming shutdowns in this dataset

gpt-4.1-2025-04-14, gpt-4.1-mini-2025-04-14, gpt-4o-2024-08-06, gpt-4o-2024-11-20, and gpt-4o-mini-2024-07-18 shut down on 2027-01-14. The official replacement on these rows is gpt-6-luna.

gpt-4.1, gpt-4.1-mini, gpt-4o, and gpt-4o-mini have no shutdown date on their own records. A request that sends the short id is not the dated snapshot row. Open the model page before you treat the short id as shut down.

Rows are upcoming OpenAI chat models in the gpt-4o, gpt-4.1, gpt-4-turbo, gpt-4, and gpt-3.5-turbo families. Audio, realtime, transcribe, and search ids are not in this table. The same id on another platform is in the other-platforms column. The full calendar is upcoming shutdowns. Provider wording for the shutdown day is on what happens on shutdown day.

Detect a dying model

These checks read SunsetDiff. They do not call the model provider.

• upcoming.json lists dated shutdowns in the next 90 days. No API key. Field notes are on the API docs.
• lookup/gpt-4o.json reads one id. Replace gpt-4o with the string in your config.
• The MCP server tools are check_model, upcoming_shutdowns, migration_diff, and scan_text.
• A status badge shows the stored status for a model page.
• The scan page builds a local search for retiring ids. Nothing is uploaded.

Questions