Vercel AI SDK: where a deprecated model id lives

Where the model id lives

The AI SDK OpenAI guide creates a language model with openai('model-id'). The example string on that page is gpt-6-astra. generateText and streamText take that model object.

The provider reads the credential from the OPENAI_API_KEY environment variable. This page does not show a key.

The guide does not document a fallback list. Ordered backups are on the LiteLLM and OpenRouter sections of the swap guide.

import { openai } from "@ai-sdk/openai";
import { generateText } from "ai";

const { text } = await generateText({
  model: openai("gpt-6-astra"),
  prompt: "Hello",
});

Source: AI SDK OpenAI guide , checked October 25, 2026.

How to pin or swap it

The string you pass is the id that is sent. There is no separate alias field on this factory. Replace gpt-4o, or whichever id you pass, with the official replacement from the table.

openai('id'), openai.responses('id'), and openai.chat('id') are three factories. Swap the string inside the factory you already call, unless you also need to change which API is used.

Source: AI SDK OpenAI guide , checked October 25, 2026.

GPT-6 function tools

The guide says the default OpenAI model factory, openai('model-id'), uses the Responses API. Since AI SDK 5 that is the default unless you select openai.chat. Use openai.chat('model-id') when a custom base URL implements Chat Completions and not Responses.

The same guide says to use the Responses API for GPT-6 tool calling. It also says GPT-6 Astra and GPT-6.1 Sol do not support reasoning effort none. GPT-6 Sol and GPT-6 Luna do. The error pages are the write-up for the Chat Completions failure.

import { openai } from "@ai-sdk/openai";

const model = openai.chat("gpt-6-astra");

Sources: AI SDK OpenAI guide , 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