Deprecation

Deprecation refers to the process of retiring older models or endpoints in favor of hosting better models with better capabilities for you to leverage. When we announce that a model or endpoint is being deprecated, we will provide a shutdown date on which the model or endpoint will no longer be accessible. As such, your applications relying on Groq may need occasional updates to continue working.

Once a model is announced as deprecated, make sure to migrate usage to a recommended replacement before the shutdown date to avoid failing requests. All API deprecations along with recommended replacements are listed below.

Deprecation History

January 24, 2025: Llama 3.1 70B and Llama 3.1 70B (Speculative Decoding)

On December 6, 2024, in partnership with Meta, we released llama-3.3-70b-versatile and llama-3.3-70b-specdec, and notified users that we would deprecate their 3.1 counterparts in favor of hosting Llama 3.3 with significant quality improvements for a better experience.

To facilitate a smooth transition, we will maintain the current llama-3.1-70b-versatile and llama-3.1-70b-specdec model IDs until December 20, 2024. At that time, requests to these model IDs will automatically upgrade to their respective 3.3 versions. Beginning January 24, 2025, requests to both 3.1 model IDs will return errors.

While these new models deliver improved quality, they may produce different responses than their predecessors. We recommend migrating to explicitly using llama-3.3-70b-versatile and llama-3.3-70b-specdec before December 20, 2024, for testing.

January 6, 2025: Llama 3 Groq Tool Use Models

On January 6th, we deprecated our preview versions of Llama 3 fine-tuned for tool use, llama3-groq-8b-8192-tool-use-preview and llama3-groq-70b-8192-tool-use-preview, from GroqCloud™ in favor of transitioning users to our production-ready llama-3.30-70b-versatile model.

Users of the tool use models were notified about the upcoming deprecation via email. The recommended replacement model, llama-3.3-70b-versatile, offers superior tool use capabilities and we strongly encourage users to migrate applications to this model for improved reliability and performance.

December 18, 2024: Gemma 7B

On December 11, 2024, we emailed all Gemma 7B users that we would deprecate it in favor of keeping the Gemma 9B model as it offers better performance.

November 25, 2024: Llama 3.2 90B Text Preview

In November 2024, we emailed all Llama 3.2 90B Text Preview users that we would deprecate it in favor of hosting the Llama 3.2 90B Vision Preview model for vision capabilities.

October 18, 2024: LLaVA 1.5 7B and Llama 3.2 11B Text Preview

In September 2024, we made Meta's Llama 3.2 vision models available on GroqCloud and emailed all LLaVA 1.5 7B and Llama 3.2 11B Text Preview users that we would deprecate it in favor of hosting Llama 3.2 11B Vision for better performance and more robust vision capabilities.