OpenAI RETIRED TRIVIAL

chatgpt-4o-latest — Retired

Deprecated
Shutdown
2026-02-17
Status
deprecated
Replacement
gpt-5.1-chat-latest

Quick fix — copy & paste

Choose your language. The "before" block matches the deprecated call; the "after" block is the drop-in replacement.

Breaks on 2026-02-17
# OpenAI: chatgpt-4o-latest (deprecated)
model = "chatgpt-4o-latest"
Use this instead
# Replacement
model = "gpt-5.1-chat-latest"

This migration was generated automatically from the model rename. If your code does more than swap a model id, double-check request/response shapes against the official OpenAI migration guide.

Error messages

Seeing one of these? You're in the right place.

  • model_not_found: chatgpt-4o-latest
  • The model `chatgpt-4o-latest` has been deprecated
  • The model `chatgpt-4o-latest` does not exist or you do not have access to it

Replacement options

Other OpenAI deprecations

What this means for your code

chatgpt-4o-latest is a general-purpose chat model used through the standard messages or chat completions endpoint. Most production traffic on chat models comes from streaming responses, function calling, and tool use. After the shutdown date, every API call returns an error and your app breaks for end users until the model id is updated.

chatgpt-4o-latest was retired by OpenAI on 2026-02-17. API calls now return an error and the model is no longer accessible. New code should use gpt-5.1-chat-latest; legacy code that still references this model id needs to be updated immediately.

Find every call in your codebase

Before you change anything, locate every place the deprecated model id is referenced. Search source files, environment files, feature flags, and config repos. Use these commands from your project root:

Python projects

grep -rn '"chatgpt-4o-latest"' --include="*.py" .

JavaScript / TypeScript projects

grep -rn '"chatgpt-4o-latest"' --include="*.{js,ts,tsx,jsx}" .

Anywhere (configs, scripts, infra)

grep -rn "chatgpt-4o-latest" .

Migration checklist

Steps in order. Skip any that don't apply, but read the whole list — for chat models, the non-obvious steps are usually the ones that break in production.

  1. 1. Search for the deprecated model id in your application code, environment variables, and feature flags
  2. 2. Update the model id in your API client configuration
  3. 3. Re-run integration tests that exercise streaming, function calling, and structured outputs
  4. 4. If you use prompt caching, verify the new model supports the same cache scopes
  5. 5. Compare token costs on a representative sample of prompts before deploying

Will this migration cost more?

Switching from chatgpt-4o-latest to gpt-5.1-chat-latest could change your costs significantly. Calculate the exact difference for your prompts.

Open the cost calculator →