As we launch safer and more capable models, we regularly retire older models. Software relying on OpenAI models may need occasional updates to keep working. Impacted customers will always be notified by email and in our documentation along with blog posts for larger changes.
This page lists all API deprecations, along with recommended replacements.
As announced in March 2023, we regularly release new versions of gpt-4 and gpt-3.5-turbo.
Each model version is dated with an -MMDD suffix; e.g., gpt-4-0613. The undated model name, e.g., gpt-4, will typically point to the latest version (e.g. gpt-4 points to gpt-4-0613). Users of undated model names will be notified by email typically 2 weeks before any change takes place.
After a new version is launched, older versions will typically be deprecated 3 months later.
Once a model is deprecated, be sure to migrate all usage to a suitable replacement before the shutdown date. Requests to models past the shutdown date will fail.
To help measure the performance of replacement models on your tasks, we have open-sourced Evals, a Python framework for evaluating language models.
If new models perform worse on your tasks, let us know by by submitting a pull request to our Evals repo with examples of the task.
All deprecations are listed below, with the most recent announcements at the top.
On August 22nd, 2023, we announced the new fine-tuning API (/v1/fine_tuning/jobs) and that the original /v1/fine-tunes API along with legacy models (including those fine-tuned with the /v1/fine-tunes API) will be shut down on January 04, 2024.
| Shutdown date | System | Recommended replacement |
|---|---|---|
| 2024-01-04 | /v1/fine-tunes | /v1/fine_tuning/jobs |
On July 06, 2023, we announced the upcoming retirements of older GPT-3 and GPT-3.5 models served via the completions endpoint. We also announced the upcoming retirement of our first-generation text embedding models. They will be shut down on January 04, 2024.
| Shutdown date | Model | Price | Recommended replacement |
|---|---|---|---|
| 2024-01-04 | text-ada-001 | $0.0004 / 1K tokens | gpt-3.5-turbo-instruct |
| 2024-01-04 | text-babbage-001 | $0.0005 / 1K tokens | gpt-3.5-turbo-instruct |
| 2024-01-04 | text-curie-001 | $0.0020 / 1K tokens | gpt-3.5-turbo-instruct |
| 2024-01-04 | text-davinci-001 | $0.0200 / 1K tokens | gpt-3.5-turbo-instruct |
| 2024-01-04 | text-davinci-002 | $0.0200 / 1K tokens | gpt-3.5-turbo-instruct |
| 2024-01-04 | text-davinci-003 | $0.0200 / 1K tokens | gpt-3.5-turbo-instruct |
| Shutdown date | Model | Price | Recommended replacement |
|---|---|---|---|
| 2024-01-04 | ada | $0.0004 / 1K tokens | babbage-002 |
| 2024-01-04 | babbage | $0.0005 / 1K tokens | babbage-002 |
| 2024-01-04 | curie | $0.0020 / 1K tokens | davinci-002 |
| 2024-01-04 | davinci | $0.0200 / 1K tokens | davinci-002 |
| 2024-01-04 | code-davinci-002 | free to researchers | gpt-3.5-turbo-base |
| Shutdown date | Model/System | Recommended replacement |
|---|---|---|
| 2024-01-04 | text-davinci-edit-001 | gpt-4 |
| 2024-01-04 | code-davinci-edit-001 | gpt-4 |
| 2024-01-04 | /v1/edits | /v1/chat/completions |
| Shutdown date | Model | Training price | Usage price | Recommended replacement |
|---|---|---|---|---|
| 2024-01-04 | ada | $0.0004 / 1K tokens | $0.0016 / 1K tokens | babbage-002 |
| 2024-01-04 | babbage | $0.0006 / 1K tokens | $0.0024 / 1K tokens | babbage-002 |
| 2024-01-04 | curie | $0.003 / 1K tokens | $0.012 / 1K tokens | davinci-002 |
| 2024-01-04 | davinci | $0.03 / 1K tokens | $0.12 / 1K tokens | davinci-002, gpt-3.5-turbo, gpt-4 |
| Shutdown date | Model | Price | Recommended replacement |
|---|---|---|---|
| 2024-01-04 | text-similarity-ada-001 | $0.004 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | text-search-ada-doc-001 | $0.004 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | text-search-ada-query-001 | $0.004 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | code-search-ada-code-001 | $0.004 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | code-search-ada-text-001 | $0.004 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | text-similarity-babbage-001 | $0.005 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | text-search-babbage-doc-001 | $0.005 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | text-search-babbage-query-001 | $0.005 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | code-search-babbage-code-001 | $0.005 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | code-search-babbage-text-001 | $0.005 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | text-similarity-curie-001 | $0.020 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | text-search-curie-doc-001 | $0.020 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | text-search-curie-query-001 | $0.020 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | text-similarity-davinci-001 | $0.200 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | text-search-davinci-doc-001 | $0.200 / 1K tokens | text-embedding-ada-002 |
| 2024-01-04 | text-search-davinci-query-001 | $0.200 / 1K tokens | text-embedding-ada-002 |
On June 13, 2023, we announced new chat model versions in the Function calling and other API updates blog post. The three original versions will be retired in June 2024 at the earliest.
| Shutdown date | Model | Price | Recommended replacement |
|---|---|---|---|
| at earliest 2024-06-13 | gpt-3.5-turbo-0301 | $0.0015 / 1K input tokens + $0.0020 / 1K output tokens | gpt-3.5-turbo-0613 |
| at earliest 2024-06-13 | gpt-4-0314 | $0.03 / 1K input tokens + $0.06 / 1K output tokens | gpt-4-0613 |
| at earliest 2024-06-13 | gpt-4-32k-0314 | $0.06 / 1K input tokens + $0.12 / 1K output tokens | gpt-4-32k-0613 |
| Shutdown date | Model | Recommended replacement |
|---|---|---|
| 2023-03-23 | code-davinci-002 | gpt-4 or researcher access program |
| 2023-03-23 | code-davinci-001 | gpt-4 or researcher access program |
| 2023-03-23 | code-cushman-002 | gpt-4 or researcher access program |
| 2023-03-23 | code-cushman-001 | gpt-4 or researcher access program |
| Shutdown date | System | Recommended replacement |
|---|---|---|
| 2022-12-03 | /v1/engines | /v1/models |
| 2022-12-03 | /v1/search | View transition guide |
| 2022-12-03 | /v1/classifications | View transition guide |
| 2022-12-03 | /v1/answers | View transition guide |