Deprecated Model → Replacement Guide
| Deprecated Model | Provider | Status | Recommended Replacement | Notes |
|---|---|---|---|---|
gpt-4-0125-preview | OpenAI | deprecated | gpt-4o | GPT-4 Turbo preview → GPT-4o. Faster, cheaper, multimodal. |
gpt-3.5-turbo-0125 | OpenAI | deprecated | gpt-4o-mini | GPT-3.5 Turbo → GPT-4o Mini. Similar price tier, better quality. |
gpt-4-turbo | OpenAI | deprecated | gpt-4o | GPT-4 Turbo → GPT-4o. GPT-4o is faster and cheaper. |
text-davinci-003 | OpenAI | deprecated | gpt-4o-mini | Legacy Davinci completion model. Migrate to chat completions API. |
claude-2.0 | Anthropic | deprecated | claude-3-5-haiku | Claude 2 → Claude 3.5 Haiku. Similar price, dramatically better performance. |
claude-instant-1.2 | Anthropic | deprecated | claude-3-5-haiku | Claude Instant → Claude 3.5 Haiku. Much better quality at comparable cost. |
llama3-70b-8192 (Groq) | Groq | disabled | llama-3.3-70b | Llama 3 70B → Llama 3.3 70B. Drop-in replacement with better benchmarks. |
claude-3-5-sonnet-20241022 | anthropic | disabled | claude-sonnet-4-20250514 | Deprecated 2025-10-22 |
claude-3-5-sonnet-20240620 | anthropic | disabled | claude-sonnet-4-20250514 | Deprecated 2025-10-22 |
Migration Tips
Test before switching
Run your evaluation set on the new model before cutting over. Newer models often have different output style, token counting, and function-calling behavior.
Update your model string
Most migrations only require changing the model parameter in your API call. For OpenAI migrations, also check that you are using the Chat Completions API (not the legacy Completions endpoint).
Context window changes
Replacement models often have larger context windows. If you were truncating inputs to fit the old model's limit, you may be able to remove that logic.
Compare benchmark data
Check the live benchmarks page to compare throughput and latency between the old and new model before committing.
Frequently Asked Questions
What should I use instead of gpt-4-0125-preview?
Migrate to gpt-4o. It is faster, cheaper, and multimodal. If you were using GPT-4 Turbo preview for cost efficiency, gpt-4o-mini is even cheaper and handles most tasks well.
What replaces gpt-3.5-turbo?
GPT-4o Mini (gpt-4o-mini) is the recommended replacement. It is comparable in price to GPT-3.5 Turbo and significantly better at instruction-following and reasoning.
What replaces Claude 2?
Claude 3.5 Haiku is Anthropic's recommended replacement for Claude 2 and Claude Instant. It offers much better performance at similar pricing.
How do I know if my model is deprecated?
Check the model's page on this site — deprecated models show a warning banner. You can also check the provider's official deprecation schedule in their documentation.
Will deprecated model APIs still work?
Providers typically give a deprecation window (often 3–6 months) before shutting down endpoints. After the shutdown date, API calls to the deprecated model will fail. Always migrate before the stated end-of-life date.