# cross-encoder/ms-marco-minilm-l-12-v2 — Withdrawn — shutdown 8 August 2026

For cross-encoder/ms-marco-minilm-l-12-v2, provider is IBM watsonx.ai; lifecycle status is Withdrawn; deprecation announced is 8 May 2026; shutdown / retirement date is 8 August 2026; recommended replacement is granite-embedding-278m-multilingual, multilingual-e5-large; platform / deployment scope is watsonx.ai embedding models (Dallas, Frankfurt, London, Tokyo, Sydney, Toronto, AWS Mumbai, AWS GovCloud data centers), recorded from its source on 2026-09-16.

- **Provider:** IBM watsonx.ai _(our reading, not quoted from the source)_
- **Model ID / API name:** cross-encoder/ms-marco-minilm-l-12-v2 _(verified: appears in the quote below)_
- **Human-readable model name:** ms-marco-minilm-l-12-v2 _(verified: appears in the quote below)_
- **Lifecycle status:** Withdrawn
- **Release date:** 21 October 2024 _(verified: appears in its own passage below)_
- **Deprecation announced:** 8 May 2026 _(verified: appears in the quote below)_
- **Shutdown / retirement date:** 8 August 2026 _(verified: appears in the quote below)_
- **Recommended replacement:** granite-embedding-278m-multilingual, multilingual-e5-large _(verified: appears in the quote below)_
- **Platform / deployment scope:** watsonx.ai embedding models (Dallas, Frankfurt, London, Tokyo, Sydney, Toronto, AWS Mumbai, AWS GovCloud data centers) _(our reading, not quoted from the source)_

## What the source says

> ms-marco-minilm-l-12-v2 (Dallas, Frankfurt, London, Tokyo, Sydney, Toronto, AWS Mumbai, AWS GovCloud data centers) cross-encoder/ms-marco-minilm-l-12-v2 | 21 October 2024 | 8 May 2026 | 8 August 2026 | granite-embedding-278m-multilingual, multilingual-e5-large |

## Where each value comes from

This source states these in separate places, so each value is shown with the passage that states it.

### Release date

> Foundation model name API model ID | Availability date | Deprecation date | Withdrawal date | Recommended alternative model | slate-30m-english-rtrvr-v2 (Frankfurt, London, Tokyo, Sydney, Toronto, AWS Mumbai, AWS GovCloud data centers) ibm/slate-30m-english-rtrvr-v2 | 15 August 2024 | 8 May 2026 | 12 January 2027 | granite-embedding-278m-multilingual, multilingual-e5-large | slate-30m-english-rtrvr-v2 (Dallas data center only) ibm/slate-30m-english-rtrvr-v2 | 15 August 2024 | 8 May 2026 | 12 January 2027 | granite-embedding-278m-multilingual, multilingual-e5-large | slate-125m-english-rtrvr-v2 (Dallas, Frankfurt, London, Tokyo, Sydney, Toronto, AWS Mumbai, AWS GovCloud data centers) ibm/slate-125m-english-rtrvr-v2 | 15 August 2024 | 8 May 2026 | 12 January 2027 | granite-embedding-278m-multilingual, multilingual-e5-large | all-minilm-l6-v2 (Dallas, Frankfurt, London, Tokyo data centers) sentence-transformers/all-minilm-l6-v2 | 29 October 2024 | 8 May 2026 | 12 January 2027 | granite-embedding-278m-multilingual, multilingual-e5-large | ms-marco-minilm-l-12-v2 (Dallas, Frankfurt, London, Tokyo, Sydney, Toronto, AWS Mumbai, AWS GovCloud data centers) cross-encoder/ms-marco-minilm-l-12-v2 | 21 October 2024 | 8 May 2026 | 8 August 2026 | granite-embedding-278m-multilingual, multilingual-e5-large |

## Source

- https://www.ibm.com/docs/en/watsonx/saas?topic=models-foundation-model-lifecycle

Last verified: 2026-09-16. Review by: 2026-10-16.
Part of [AI model deprecation and retirement dates by provider](https://referencesource.org/ai-model-deprecation-and-retirement/).