SunsetDiff

Retired Nebius Token Factory models

21 Nebius Token Factory model records have status retired, sorted by shutdown date. The stored status is retired. The dataset records these models as already shut down. Every record on this page has a shutdown date. Each row links the model page and the replacement page. The official page is https://docs.tokenfactory.nebius.com/model-deprecations-november-2026. The model page records the day that page was checked. Last updated 2026-11-10, the dataset version (the newest changelog date). See all retired models. What retired means is on Retired.

Nebius Token Factory: 21 retired models, sorted by shutdown date.
ModelShutdownReplacement
deepseek-ai/DeepSeek-V4-Flash
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-08-31
source, checked 2026-11-12
deepseek-ai/DeepSeek-V4-Flash-0731 (official)
meta-llama/Llama-3.3-70B-Instruct
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-08-31
source, checked 2026-11-12
nvidia/Nemotron-3_5-Lightning (official)
MiniMaxAI/MiniMax-M2.5
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-08-31
source, checked 2026-11-12
MiniMaxAI/MiniMax-M3 (official)
NousResearch/Hermes-4-70B
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-08-31
source, checked 2026-11-12
nvidia/Nemotron-3_5-Lightning (official)
nvidia/Cosmos3-Super-Reasoner
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-08-31
source, checked 2026-11-12
MiniMaxAI/MiniMax-M3 (official)
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-08-31
source, checked 2026-11-12
nvidia/nemotron-3-super-120b-a12b (official)
nvidia/Nemotron-3-Nano-Omni
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-08-31
source, checked 2026-11-12
nvidia/Nemotron-3_5-Lightning (official)
Qwen/Qwen2.5-VL-72B-Instruct
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-08-31
source, checked 2026-11-12
MiniMaxAI/MiniMax-M3 (official)
Qwen/Qwen3-32B
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-08-31
source, checked 2026-11-12
nvidia/Nemotron-3_5-Lightning (official)
Qwen/Qwen3-Next-80B-A3B-Thinking
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-08-31
source, checked 2026-11-12
Qwen/Qwen3.5-397B-A17B (official)
deepseek-ai/DeepSeek-V4-Flash-0731
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-11-09
source, checked 2026-11-12
deepseek-ai/DeepSeek-V4.1-Flash-1017 (official)
deepseek-ai/DeepSeek-V4-Pro
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-11-09
source, checked 2026-11-12
deepseek-ai/DeepSeek-V4-Pro-0813 (official)
deepseek-ai/DeepSeek-V4.1-Flash
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-11-09
source, checked 2026-11-12
deepseek-ai/DeepSeek-V4.1-Flash-1017 (official)
moonshotai/Kimi-K2.6
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-11-09
source, checked 2026-11-12
moonshotai/Kimi-K3 (official)
moonshotai/Kimi-K2.7-Code
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-11-09
source, checked 2026-11-12
moonshotai/Kimi-K3 (official)
nvidia/nemotron-3-super-120b-a12b
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-11-09
source, checked 2026-11-12
nvidia/Nemotron-3.5-Super-VL (official)
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-11-09
source, checked 2026-11-12
nvidia/Nemotron-3_5-Lightning (official)
openbmb/MiniCPM-V-4_5
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-11-09
source, checked 2026-11-12
nvidia/Nemotron-3.5-Super-VL (official)
Qwen/Qwen3-235B-A22B-Instruct-2507
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-11-09
source, checked 2026-11-12
Qwen/Qwen3-30B-A3B-Instruct-2507 (official)
Qwen/Qwen3.5-397B-A17B
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-11-09
source, checked 2026-11-12
Qwen/Qwen3.8-27B (official)
zai-org/GLM-5.1
This change only affects Serverless usage. Dedicated Endpoints are unaffected. Token Factory does not automatically reroute requests from deprecated models.
2026-11-09
source, checked 2026-11-12
zai-org/GLM-5.3 (official)

Questions

How many Nebius Token Factory models are retired?

21 Nebius Token Factory model records have status retired.

What is the latest shutdown date among retired Nebius Token Factory models?

The latest shutdown date on a retired model record is 2026-11-09. 11 retired model records share that date, including deepseek-ai/DeepSeek-V4-Flash-0731 (Nebius Token Factory).

How many retired Nebius Token Factory models list a replacement?

21 of 21 retired model records list a replacement. The table links each replacement page.