llama-3.3-70b-versatile
Shut down
Replacement
openai/gpt-oss-120b or qwen/qwen3.6-27bInference APIs has no upcoming shutdown dates published. In the last 12 months 7 models were retired or shut down, most recently llama-3.3-70b-versatile on Aug 16, 2026.
Inference APIs has not published an upcoming shutdown date for any tracked model.
llama-3.3-70b-versatileopenai/gpt-oss-120b or qwen/qwen3.6-27bllama-3.1-8b-instantopenai/gpt-oss-20bqwen/qwen3-32bopenai/gpt-oss-120bopenai/gpt-oss-120b or qwen/qwen3.6-27bmoonshotai/kimi-k2-instruct-0905openai/gpt-oss-120bopenai/gpt-oss-120bmeta-llama/llama-guard-4-12bopenai/gpt-oss-safeguard-20bEach provider and hosting route sets its own dates. A model offered on several platforms can stop on different days; ModelClock reads each notice from the provider's own documentation.