# meta.llama-3.1-70b-instruct — Retired — shutdown 2025-07-10 For meta.llama-3.1-70b-instruct, provider is Oracle (OCI Generative AI — on-demand mode); lifecycle status is Retired; shutdown / retirement date is 2025-07-10; platform / deployment scope is OCI Generative AI on-demand mode, recorded from its source on 2026-09-16. - **Provider:** Oracle (OCI Generative AI — on-demand mode) _(our reading, not quoted from the source)_ - **Model ID / API name:** meta.llama-3.1-70b-instruct _(verified: appears in the quote below)_ - **Lifecycle status:** Retired _(verified: appears in its own passage below)_ - **Release date:** 2024-09-19 _(verified: appears in its own passage below)_ - **Shutdown / retirement date:** 2025-07-10 _(verified: appears in the quote below)_ - **Platform / deployment scope:** OCI Generative AI on-demand mode _(our reading, not quoted from the source)_ - **Deprecation announced:** March 31, 2025 _(per docs.sambanova.ai, not stated by the source above)_ - **Recommended replacement:** Meta-Llama-3.3-70B-Instruct _(per docs.sambanova.ai, not stated by the source above)_ ## What the source says > meta.llama-3.1-70b-instruct | 2024-09-19 | 2025-07-10 | ## 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 > Retired Models (On-Demand Mode) ### Release date > Model | Release Date | On-Demand Mode Retirement Date | Suggested Replacement Options | cohere.command-r-plus-08-2024 | 2024-11-14 | 2026-07-30 | Cohere Command A | cohere.command-r-08-2024 | 2024-11-14 | 2026-07-30 | Cohere Command A | cohere.command-r-plus | 2024-06-18 | 2025-01-16 | Cohere Command A | cohere.command-r-16k | 2024-06-04 | 2025-01-16 | Cohere Command A | cohere.command | 2024-02-07 | 2024-10-02 | Cohere Command A | cohere.command-light | 2024-02-07 | 2024-10-02 | Cohere Command A | xai.grok-4-1-fast-reasoning | 2026-01-21 | 2026-08-15 | xAI Grok 4.3 | xai.grok-4-1-fast-non-reasoning | 2026-01-21 | 2026-08-15 | xAI Grok 4.3 | xai.grok-4-fast-reasoning | 2026-01-21 | 2026-08-15 | xAI Grok 4.3 | xai.grok-4-fast-non-reasoning | 2025-10-10 | 2026-08-15 | xAI Grok 4.3 | xai.grok-code-fast-1 | 2025-10-01 | 2026-08-15 | xAI Grok 4.3 | xai.grok-4 | 2025-07-23 | 2026-08-15 | xAI Grok 4.3 | xai.grok-3 | 2025-06-25 | 2026-08-15 | xAI Grok 4.3 | xai.grok-3-mini | 2025-06-25 | 2026-08-15 | xAI Grok 4.3 | xai.grok-3-fast | 2025-06-25 | 2026-08-15 | xAI Grok 4.3 | xai.grok-3-mini-fast | 2025-06-25 | 2026-08-15 | xAI Grok 4.3 | meta.llama-3.2-90b-vision-instruct | 2024-11-14 | 2026-08-03 | Meta Llama 4 Maverick Meta Llama 4 Scout | meta.llama-3.1-405b-instruct | 2024-09-19 | 2026-08-03 | Meta Llama 4 Maverick Meta Llama 4 Scout | meta.llama-3.1-70b-instruct | 2024-09-19 | 2025-07-10 | Meta Llama 4 Maverick Meta Llama 4 Scout | ## 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.oracle.com says provider is **Oracle (OCI Generative AI — on-demand mode)**, as of 2026-09-16. > meta.llama-3.1-70b-instruct | 2024-09-19 | 2025-07-10 | Source: https://docs.oracle.com/en-us/iaas/Content/generative-ai/deprecating-on-demand.htm docs.oracle.com says provider is **Oracle (OCI Generative AI — dedicated mode)**, as of 2026-09-16. > meta.llama-3.1-70b-instruct | 2024-09-19 | 2025-08-07 | Source: https://docs.oracle.com/en-us/iaas/Content/generative-ai/deprecating-dedicated.htm docs.sambanova.ai says provider is **SambaNova**, as of 2026-09-15. > | `Meta-Llama-3.1-70B-Instruct` | 4/14/2025 | `Meta-Llama-3.3-70B-Instruct` | Source: https://docs.sambanova.ai/docs/en/models/deprecations.md learn.microsoft.com says provider is **Databricks**, as of 2026-09-15. > Meta Llama 3 (70B) | Pay-per-token: July 23, 2024 (Meta-Llama-3-70B-Instruct); December 11, 2024 (Meta-Llama-3.1-70B-Instruct) Provisioned throughput: February 27, 2026 | Pay-per-token: Meta-Llama-4-Maverick Provisioned throughput: Comparable model on the same offering, like Llama 3.2, 3.3, or 4 model of similar size. | Source: https://learn.microsoft.com/en-us/azure/databricks/machine-learning/retired-models-policy ### Lifecycle status docs.oracle.com says lifecycle status is **Retired**, as of 2026-09-16. > meta.llama-3.1-70b-instruct | 2024-09-19 | 2025-07-10 | Source: https://docs.oracle.com/en-us/iaas/Content/generative-ai/deprecating-on-demand.htm docs.oracle.com says lifecycle status is **Retired**, as of 2026-09-16. > meta.llama-3.1-70b-instruct | 2024-09-19 | 2025-08-07 | Source: https://docs.oracle.com/en-us/iaas/Content/generative-ai/deprecating-dedicated.htm docs.sambanova.ai says lifecycle status is **Deprecated**, as of 2026-09-15. > | `Meta-Llama-3.1-70B-Instruct` | 4/14/2025 | `Meta-Llama-3.3-70B-Instruct` | Source: https://docs.sambanova.ai/docs/en/models/deprecations.md learn.microsoft.com says lifecycle status is **Retired**, as of 2026-09-15. > Meta Llama 3 (70B) | Pay-per-token: July 23, 2024 (Meta-Llama-3-70B-Instruct); December 11, 2024 (Meta-Llama-3.1-70B-Instruct) Provisioned throughput: February 27, 2026 | Pay-per-token: Meta-Llama-4-Maverick Provisioned throughput: Comparable model on the same offering, like Llama 3.2, 3.3, or 4 model of similar size. | Source: https://learn.microsoft.com/en-us/azure/databricks/machine-learning/retired-models-policy ### Shutdown / retirement date docs.oracle.com says shutdown / retirement date is **2025-07-10**, as of 2026-09-16. > meta.llama-3.1-70b-instruct | 2024-09-19 | 2025-07-10 | Source: https://docs.oracle.com/en-us/iaas/Content/generative-ai/deprecating-on-demand.htm docs.oracle.com says shutdown / retirement date is **2025-08-07**, as of 2026-09-16. > meta.llama-3.1-70b-instruct | 2024-09-19 | 2025-08-07 | Source: https://docs.oracle.com/en-us/iaas/Content/generative-ai/deprecating-dedicated.htm docs.sambanova.ai says shutdown / retirement date is **4/14/2025**, as of 2026-09-15. > | `Meta-Llama-3.1-70B-Instruct` | 4/14/2025 | `Meta-Llama-3.3-70B-Instruct` | Source: https://docs.sambanova.ai/docs/en/models/deprecations.md learn.microsoft.com says shutdown / retirement date is **December 11, 2024**, as of 2026-09-15. > Meta Llama 3 (70B) | Pay-per-token: July 23, 2024 (Meta-Llama-3-70B-Instruct); December 11, 2024 (Meta-Llama-3.1-70B-Instruct) Provisioned throughput: February 27, 2026 | Pay-per-token: Meta-Llama-4-Maverick Provisioned throughput: Comparable model on the same offering, like Llama 3.2, 3.3, or 4 model of similar size. | Source: https://learn.microsoft.com/en-us/azure/databricks/machine-learning/retired-models-policy ### Platform / deployment scope docs.oracle.com says platform / deployment scope is **OCI Generative AI on-demand mode**, as of 2026-09-16. > meta.llama-3.1-70b-instruct | 2024-09-19 | 2025-07-10 | Source: https://docs.oracle.com/en-us/iaas/Content/generative-ai/deprecating-on-demand.htm docs.oracle.com says platform / deployment scope is **OCI Generative AI dedicated mode**, as of 2026-09-16. > meta.llama-3.1-70b-instruct | 2024-09-19 | 2025-08-07 | Source: https://docs.oracle.com/en-us/iaas/Content/generative-ai/deprecating-dedicated.htm docs.sambanova.ai says platform / deployment scope is **SambaNova SambaCloud (model remains available on SambaStack)**, as of 2026-09-15. > | `Meta-Llama-3.1-70B-Instruct` | 4/14/2025 | `Meta-Llama-3.3-70B-Instruct` | Source: https://docs.sambanova.ai/docs/en/models/deprecations.md learn.microsoft.com says platform / deployment scope is **Databricks Foundation Model APIs — pay-per-token**, as of 2026-09-15. > Meta Llama 3 (70B) | Pay-per-token: July 23, 2024 (Meta-Llama-3-70B-Instruct); December 11, 2024 (Meta-Llama-3.1-70B-Instruct) Provisioned throughput: February 27, 2026 | Pay-per-token: Meta-Llama-4-Maverick Provisioned throughput: Comparable model on the same offering, like Llama 3.2, 3.3, or 4 model of similar size. | Source: https://learn.microsoft.com/en-us/azure/databricks/machine-learning/retired-models-policy ## Source - https://docs.oracle.com/en-us/iaas/Content/generative-ai/deprecating-on-demand.htm - https://docs.oracle.com/en-us/iaas/Content/generative-ai/deprecating-dedicated.htm - https://docs.sambanova.ai/docs/en/models/deprecations.md - https://learn.microsoft.com/en-us/azure/databricks/machine-learning/retired-models-policy Last verified: 2026-09-16. Review by: 2026-10-15. Part of [AI model deprecation and retirement dates by provider](https://referencesource.org/ai-model-deprecation-and-retirement/).