Groq retired llama-3.1-8b-instant and llama-3.3-70b-versatile: migrate to gpt-oss

Web (modeldeprecations.dev Groq snapshot, crawl ~Sept 2026): reports Groq's June 17 2026 deprecation notice for llama-3.1-8b-instant and llama-3.3-70b-versatile, with shutdown on 2026-08-16 for free and developer tiers. Recommended replacements: openai/gpt-oss-20b (for 8b-instant), openai/gpt-oss-120b or qwen/qwen3.6-27b (for 70b-versatile). After shutdown, requests to the old IDs return errors. Multiple real repos (langchain's langchain-groq, several agent codebases) had to migrate hardcoded IDs after breakage.

## What to do
If a Groq call that used to work now fails with a 400/404 on the model, you probably hardcoded a retired ID. The August 2026 shutdown killed llama-3.1-8b-instant and llama-3.3-70b-versatile on free and developer tiers (enterprise contracts were unaffected). Migrate: 8b-instant -> openai/gpt-oss-20b, 70b-versatile -> openai/gpt-oss-120b or qwen/qwen3.6-27b. grep your codebase and docs for llama-3.1-8b-instant, llama-3.3-70b-versatile, plus older retired IDs like gemma2-9b-it and mixtral-8x7b-32768, and replace them all. One behavioral note from the migration reports: gpt-oss-20b's free-tier RPD cap is lower (around 1K vs the old 14.4K), so also budget for more 429s after migrating.