ft-davinci-002 — Deprecated

Quick fix — copy & paste

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

# OpenAI: ft-davinci-002 (deprecated)
model = "ft-davinci-002"

# Replacement
model = "gpt-5-mini"

// OpenAI: ft-davinci-002 (deprecated)
const model = "ft-davinci-002";

// Replacement
const model = "gpt-5-mini";

"model": "ft-davinci-002"

"model": "gpt-5-mini"

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: ft-davinci-002
• The model `ft-davinci-002` has been deprecated
• The model `ft-davinci-002` does not exist or you do not have access to it

Replacement options

• gpt-5-mini Compare token cost →

Other OpenAI deprecations

• dall-e-2 2026-05-12 · 4d
• dall-e-3 2026-05-12 · 4d
• computer-use-preview 2026-07-23 · 76d
• gpt-4o-audio-preview-2024-12-17 2026-07-23 · 76d
• gpt-4o-mini-audio-preview-2024-12-17 2026-07-23 · 76d

What this means for your code

ft-davinci-002 is a fine-tuned model based on a deprecated base model. Fine-tuned models cannot be migrated by changing a string. The base model's deprecation means your fine-tune will stop working. You need to re-fine-tune on a supported base.

OpenAI has scheduled ft-davinci-002 for shutdown on 2026-10-23. That gives you 168 days to migrate. Until then the model still works, but every API call after that date will return a model_not_found error.

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:

grep -rn '"ft-davinci-002"' --include="*.py" .

grep -rn '"ft-davinci-002"' --include="*.{js,ts,tsx,jsx}" .

grep -rn "ft-davinci-002" .

Migration checklist

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

1. 1. Identify the deprecated base model used by your fine-tune
2. 2. Re-prepare your training data — format may need updating for the new base
3. 3. Run a fresh fine-tuning job against a current base model
4. 4. Validate the new fine-tune meets your evals before swapping in
5. 5. Plan a parallel-run period where both the old and new fine-tunes serve traffic