Minor: Updated the status of gpt-3.5-turbo-instruct to reflect its shutdown on September 28, 2026.

Summary by gemma-4-12b. It may be wrong; the diff below is what actually changed. Raw: 3d335831c2-openai-rate-limits.diff · commit 3d335831c2

diff --git a/snapshots/openai/rate-limits.md b/snapshots/openai/rate-limits.mdindex 2569436..227fc81 100644--- a/snapshots/openai/rate-limits.md+++ b/snapshots/openai/rate-limits.md@@ -151,5 +151,5 @@ This approach has many benefits: Note that unsuccessful requests contribute to your per-minute limit, so continuously resending a request won't work. -The legacy Completions examples below use `gpt-3.5-turbo-instruct`, which has a scheduled shutdown date of September 28, 2026. After that date, retain the retry pattern but migrate the request to Responses or Chat Completions with `gpt-5.6-terra`; changing the model ID in a Completions request is not sufficient.+The legacy Completions examples below use `gpt-3.5-turbo-instruct`, which was shut down on September 28, 2026. You can use the same retry pattern with current models by migrating to Responses or Chat Completions.  The Python examples below demonstrate fallback backoff. They don't inspect `Retry-After`: before using them, add handling for valid server hints so the wrappers don't retry sooner than requested. Disable SDK retries or account for them in your application's retry limits.

← OpenAI timeline