The model has been deprecated

On October 23, 2026 those model ids stop being accessible. OpenAI's deprecations page does not print the error sentence. A public GitHub issue records one for a model that was already removed.

Error text

The model `gpt-4-vision-preview` has been deprecated, learn more here: https://platform.openai.com/docs/deprecations

Quoted from GitHub issue excalidraw/excalidraw#8209, checked October 20, 2026.

OpenAI's deprecations page says: at the time of the shut down, the model or endpoint will no longer be accessible. The October 23, 2026 table names gpt-3.5-turbo-0125 (and gpt-3.5-turbo), gpt-4-0613 (and gpt-4), gpt-4-1106-preview, gpt-4-turbo, gpt-4.1-nano, gpt-4o-2024-05-13, o1, o1-pro, o3-mini, and o4-mini. The error sentence in the block above is copied from a GitHub issue about gpt-4-vision-preview, not from the October 23 table. A comment on https://github.com/BerriAI/litellm/pull/23747 records the same shape for an already removed snapshot: The model `gpt-4-0314` has been deprecated, learn more here: https://platform.openai.com/docs/deprecations The Python error guide lists NotFoundError as "Requested resource does not exist." It does not tie that type to this shutdown. Source: OpenAI deprecations, checked October 20, 2026.

Affected models

Fix

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello"}],
)

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[{"role": "user", "content": "Hello"}],
)

import litellm
response = litellm.completion(
    model="openai/gpt-5.6-sol",
    messages=[{"role": "user", "content": "Hello"}],
)

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

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  prompt: "Hello",
});

Shutdown pages

• OpenAI October 23, 2026 batch

Switch guides

• gpt-4 to gpt-5.6-sol
• gpt-3.5-turbo to gpt-5.6-terra
• gpt-4-turbo to gpt-5.6-sol
• gpt-4o-2024-05-13 to gpt-5.6-sol
• gpt-4.1-nano to gpt-5.6-luna
• o1 to gpt-5.6-sol
• o3-mini to gpt-5.6-sol
• o4-mini to gpt-5.6-terra

More request errors

• Function tools with reasoning_effort are not supported for gpt-6-luna
• Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

All request errors