LlamaIndex: where a deprecated model id lives

Where the model id lives

The using-LLMs page says you specify a model by passing model to the LLM constructor. Its example is OpenAI(model="gpt-4o-mini").

The OpenAI integration page repeats that call, including OpenAI(model="gpt-4o") and OpenAI(model="gpt-4o-mini"). It says the constructor uses the OPENAI_API_KEY environment variable by default. This page does not show a key.

The API reference says the model parameter is the name of the OpenAI model to use, and that its default is DEFAULT_OPENAI_MODEL. The customizing-LLMs page says the default LLM is OpenAI's gpt-3.5-turbo. This page does not claim those two defaults are the same string.

The Settings page says Settings.llm is the global LLM when a component does not receive one. The customizing page shows Settings.llm = OpenAI(...) and a local override, query_engine = index.as_query_engine(llm=llm).

from llama_index.llms.openai import OpenAI

llm = OpenAI(model="gpt-4o-mini")

from llama_index.core import Settings
from llama_index.llms.openai import OpenAI

Settings.llm = OpenAI(model="gpt-4o-mini")

Sources: LlamaIndex using LLMs , LlamaIndex OpenAI integration , LlamaIndex OpenAI API reference , LlamaIndex customizing LLMs , LlamaIndex Settings , checked October 25, 2026.

How to pin or swap it

Change the model string to the official replacement on the shutdown row. If Settings.llm is set, change that assignment too, or a path that omits llm= will keep the old global id.

The OpenAI integration page does not document a router alias or a fallback list. A second model is a second OpenAI(model=...) call in your code.

Sources: LlamaIndex OpenAI integration , LlamaIndex Settings , checked October 25, 2026.

GPT-6 function tools

The LlamaIndex OpenAI integration page does not document a Responses API switch. Do not add a flag this page did not find there.

OpenAI's Using GPT-6 guide says GPT-6 Astra and GPT-6.1 Sol tool calling requires the Responses API, and that GPT-6 Sol and GPT-6 Luna accept function tools on Chat Completions only with reasoning effort none. If the replacement id is one of those models, read the error pages and the Responses API guide before you send tools.

Sources: LlamaIndex OpenAI integration , 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