LiteLLM: where a model id lives when a model shuts down

Where the model id lives

The proxy config page says model_name is the name to pass to LiteLLM from the external client. litellm_params.model is the model string passed to litellm.completion(). A client can keep sending a private alias while the provider id behind it changes.

The OpenAI provider page says a model string with the openai/ prefix calls Chat Completions. Prefix one call with openai/responses/ to send that call to the Responses API. The page shows openai/responses/gpt-6.1-sol for a request that includes tools.

Credentials stay in the environment or in a credential field on the proxy. This page does not show a key.

model_list:
  - model_name: gpt-6.1-sol
    litellm_params:
      model: openai/gpt-6.1-sol

Sources: LiteLLM proxy config , LiteLLM OpenAI provider , checked October 25, 2026.

How to pin or swap it

To pin a call, put the specific provider id in the model string. To swap a shutdown, replace that id with the official replacement from the table. If applications call a model_name alias, change litellm_params.model and leave the alias in place.

The reliable completions page documents a fallbacks list on completion(). The proxy reliability page documents router_settings.fallbacks, which maps one model_name to another. Samples for both are on the swap guide.

Sources: LiteLLM proxy config , LiteLLM reliable completions , LiteLLM proxy fallbacks , checked October 25, 2026.

GPT-6 function tools

Use openai/responses/ plus the model id when the call includes function tools for a model OpenAI says must use the Responses API. The OpenAI provider page shows that prefix on gpt-6.1-sol.

OpenAI's Using GPT-6 guide says GPT-6 Astra and GPT-6.1 Sol tool calling requires the Responses API. GPT-6 Sol and GPT-6 Luna can keep function tools on Chat Completions only with reasoning effort none. The error pages quote the failure and the working requests.

import litellm
response = litellm.completion(
    model="openai/responses/gpt-6.1-sol",
    messages=[{"role": "user", "content": "Hello"}],
)

Sources: LiteLLM OpenAI provider , 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