llama-3.1-8b-instant shutdown date

llama-3.1-8b-instant shut down on 2026-08-16 per Groq's deprecation page (checked 2026-10-26). The official replacement is openai/gpt-oss-20b. The published context window changes from 131,072 tokens on llama-3.1-8b-instant to 131,072 tokens on openai/gpt-oss-20b.

Model page · Is llama-3.1-8b-instant being deprecated? · Groq · Deadlines

Sources

• Groq model deprecations — checked 2026-10-26
• Groq supported models — checked 2026-10-26