# Qwen/Qwen2.5-VL-72B-Instruct — Removed — shutdown 2026-01-05 For Qwen/Qwen2.5-VL-72B-Instruct, provider is Together AI; lifecycle status is Removed; shutdown / retirement date is 2026-01-05; platform / deployment scope is Together AI serverless inference, recorded from its source on 2026-09-15. - **Provider:** Together AI _(our reading, not quoted from the source)_ - **Model ID / API name:** Qwen/Qwen2.5-VL-72B-Instruct _(verified: appears in the quote below)_ - **Lifecycle status:** Removed _(verified: appears in its own passage below)_ - **Shutdown / retirement date:** 2026-01-05 _(verified: appears in the quote below)_ - **Platform / deployment scope:** Together AI serverless inference _(our reading, not quoted from the source)_ - **Recommended replacement:** MiniMaxAI/MiniMax-M3 _(per docs.tokenfactory.nebius.com, not stated by the source above)_ ## What the source says > | 2026-01-05 | `Qwen/Qwen2.5-VL-72B-Instruct` | No | ## Where each value comes from This source states these in separate places, so each value is shown with the passage that states it. ### Lifecycle status > The table below lists all models removed from serverless inference, most recent first. ### Platform / deployment scope > The table below lists all models removed from serverless inference, most recent first. ## Sources disagree More than one authority states this, and they do not state the same thing. Both are reproduced with the source each came from. ### Provider docs.together.ai says provider is **Together AI**, as of 2026-09-15. > | 2026-01-05 | `Qwen/Qwen2.5-VL-72B-Instruct` | No | Source: https://docs.together.ai/docs/deprecations.md docs.tokenfactory.nebius.com says provider is **Nebius Token Factory**, as of 2026-09-16. > | [`Qwen/Qwen2.5-VL-72B-Instruct`](https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct) | [`MiniMaxAI/MiniMax-M3`](https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3) | Source: https://docs.tokenfactory.nebius.com/august-2026-deprecation-notice.md ### Shutdown / retirement date docs.together.ai says shutdown / retirement date is **2026-01-05**, as of 2026-09-15. > | 2026-01-05 | `Qwen/Qwen2.5-VL-72B-Instruct` | No | Source: https://docs.together.ai/docs/deprecations.md docs.tokenfactory.nebius.com says shutdown / retirement date is **August 31, 2026**, as of 2026-09-16. > | [`Qwen/Qwen2.5-VL-72B-Instruct`](https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct) | [`MiniMaxAI/MiniMax-M3`](https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3) | Source: https://docs.tokenfactory.nebius.com/august-2026-deprecation-notice.md ### Platform / deployment scope docs.together.ai says platform / deployment scope is **Together AI serverless inference**, as of 2026-09-15. > | 2026-01-05 | `Qwen/Qwen2.5-VL-72B-Instruct` | No | Source: https://docs.together.ai/docs/deprecations.md docs.tokenfactory.nebius.com says platform / deployment scope is **Nebius Token Factory serverless (dedicated endpoints unaffected)**, as of 2026-09-16. > | [`Qwen/Qwen2.5-VL-72B-Instruct`](https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct) | [`MiniMaxAI/MiniMax-M3`](https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3) | Source: https://docs.tokenfactory.nebius.com/august-2026-deprecation-notice.md ## Source - https://docs.together.ai/docs/deprecations.md - https://docs.together.ai/docs/deprecations - https://docs.tokenfactory.nebius.com/august-2026-deprecation-notice.md Last verified: 2026-09-15. Review by: 2026-10-15. Part of [AI model deprecation and retirement dates by provider](https://referencesource.org/ai-model-deprecation-and-retirement/).