> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ollama.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Cloud model lifecycle

> Review upcoming and past retirements of Ollama's cloud models and recommended replacements.

Ollama occasionally deprecates and retires older cloud models as newer models become available. Tools and applications that depend on a retired model must be updated to use another model.

Impacted users are notified before a model is retired. Cloud model retirement does not affect local models.

## Upcoming retirements

No cloud model retirements are currently scheduled.

## Past retirements

> [accordion] September 25, 2026
>
> | Model | Recommended alternative |
> | - | - |
> | `qwen3.5:397b` | `glm-5.3` |
> | `glm-5.1` | `glm-5.2` |
> | `deepseek-v4-flash:0731` | `deepseek-v4.1-flash` |

> [accordion] July 31, 2026
>
> | Model | Recommended alternative |
> | - | - |
> | `minimax-m2.5` | `minimax-m2.7` |
> | `kimi-k2.5` | `kimi-k2.6` |

> [accordion] July 15, 2026
>
> | Model | Recommended alternative |
> | - | - |
> | `deepseek-v3.1:671b` | `deepseek-v4-flash` |
> | `deepseek-v3.2` | `deepseek-v4-flash` |
> | `devstral-2:123b` | `mistral-large-3:675b` |
> | `devstral-small-2:24b` | |
> | `ministral-3:14b` | |
> | `ministral-3:3b` | |
> | `ministral-3:8b` | |
> | `gemini-3-flash-preview` | `minimax-m3` |
> | `gemma3:12b` | `gemma4:31b` |
> | `gemma3:27b` | `gemma4:31b` |
> | `gemma3:4b` | `gemma4:31b` |
> | `glm-4.7` | `glm-5.2` |
> | `glm-5` | `glm-5.2` |
> | `minimax-m2.1` | `minimax-m3` |
> | `qwen3-coder-next` | |
> | `qwen3-coder:480b` | |

> [accordion] June 30, 2026
>
> | Model | Recommended alternative |
> | - | - |
> | `rnj-1:8b` | |

> [accordion] June 16, 2026
>
> | Model | Recommended alternative |
> | - | - |
> | `kimi-k2-thinking` | `kimi-k2.6` |
> | `kimi-k2:1t` | `kimi-k2.6` |
> | `minimax-m2` | `minimax-m3` |
> | `glm-4.6` | |
> | `qwen3-next:80b` | `qwen3.5` |
> | `qwen3-vl:235b` | `qwen3.5` |
> | `qwen3-vl:235b-instruct` | `qwen3.5` |
> | `cogito-2.1:671b` | `deepseek-v4-flash` |
