DeepSeek v4.1 Flash, DeepSeek v4.1 Flash Fast, DeepSeek v4 Flash 0731, GLM 5.2 Fast, Nemotron 3 Ultra, and gpt-oss-120b will be deprecated at 5pm PT on December 18th.
At that time, the model IDs will become inactive and return an error for all requests. Swap in the recommended model ID before the deprecation date:
DeepSeek v4.1 Flash (deepseek-ai/DeepSeek-V4.1-Flash): use DeepSeek v4.1 Flash 1017 (deepseek-ai/DeepSeek-V4.1-Flash-1017)
DeepSeek v4.1 Flash Fast (deepseek-ai/DeepSeek-V4.1-Flash-Fast): use DeepSeek v4.1 Flash 1017 Fast (deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast)
DeepSeek v4 Flash 0731 (deepseek-ai/DeepSeek-V4-Flash-0731): use DeepSeek v4.1 Flash 1017 (deepseek-ai/DeepSeek-V4.1-Flash-1017)
GLM 5.2 Fast (zai-org/GLM-5.2-Fast): use GLM 5.3 Fast (zai-org/GLM-5.3-Fast)
Nemotron 3 Ultra (nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B): use Nemotron 3.5 Super VL (nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B)
gpt-oss-120b (openai/gpt-oss-120b): use Nemotron 3.5 Super VL (nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B)