To help you discover and use the latest and best foundation models, the list of foundation models that are deployed by IBM on multitenant hardware and available for prompting in watsonx.ai is refreshed regularly.
Foundation models that are built by IBM are continuously updated and improved. As new versions of IBM foundation models are introduced, older versions remain available for you to use for at least 90 days after an updated model is introduced.
Similarly, as newer and more-effective models from other providers become available, less useful models are removed from watsonx.ai to make room for them. You are given at least 30 days notice before foundation models from other providers are removed from watsonx.ai.
Some foundation models that are withdrawn and no longer available for prompting from multitenant hardware can be deployed on demand. For more information, see Deploy on demand foundation models.
Modifications to IBM foundation models
IBM foundation models are periodically modified by IBM to improve the foundation model performance or security. A modification is a model refresh that might include new capabilities or fixes, but does not meet IBM's criteria to warrant a version update.
Foundation model modifications do not disrupt the watsonx.ai service. You can check the current full version number for an IBM foundation model at any time from the model card. The version number consists of three digits that identify the version, modification, and fix numbers that are associated with the IBM foundation model. For more information about versioning, see IBM Software product versioning explained.
Any applications that inference an IBM foundation model that is modified will pick up the modifications, including any changes in performance or in the output that is generated by the model.
Foundation model deprecation
During the deprecation period, you can continue to inference the deprecated foundation model. However, a message is returned with the foundation model output to notify you about the upcoming model removal.
A deprecated foundation model can also be constricted. When a deprecated model is in the constricted state, it means the model can be inferenced, but cannot be tuned, trained, or deployed.
When a foundation model is deprecated, the following steps are taken to inform you about the deprecation:
- The foundation model is highlighted in the product user interface with a warning icon
. A tooltip indicates that the deprecated model is scheduled
for withdrawal. - The deprecation is announced in the What’s new topic of the product documentation. The release note clearly states the deprecation date and withdrawal date for the foundation model.
- The Deprecated foundation models table is updated to show the foundation model that is being deprecated, the dates of deprecation and withdrawal, and a suitable alternative foundation model for you to consider as a replacement.
Deprecated models
The following table lists the foundation models that are deprecated.
| Foundation model name | API model ID | Deprecation date | Withdrawal date | Alternative foundation model |
|---|---|---|---|---|
| llama-3-1-8b-instruct | meta-llama/llama-3-1-8b-instruct |
22 January 2025 | 30 May 2025 | llama-3-2-11b-vision-instruct |
| llama-3-1-70b-instruct | meta-llama/llama-3-1-70b-instruct |
22 January 2025 | 30 May 2025 | llama-3-3-70b-instruct, llama-3-2-90b-vision-instruct |
| granite-20b-multilingual | ibm/granite-20b-multilingual |
15 January 2025 | 16 April 2025 | granite-3-8b-instruct |
| codellama-34b-instruct | codellama/codellama-34b-instruct-hf |
15 January 2025 | 31 March 2025 | llama-3-3-70b-instruct |
| llama-3-70b-instruct (Sydney data center) |
meta-llama/llama-3-70b-instruct |
2 December 2024 | 31 March 2025 | llama-3-3-70b-instruct, llama-3-2-90b-vision-instruct |
| llama-2-13b-chat | meta-llama/llama-2-13b-chat |
26 August 2024 | – | llama-3-2-11b-vision-instruct |
Planned deprecations
The following table shows the models that are planned for upcoming deprecation. The exact deprecation dates, withdrawal dates, and other details might change.
| Foundation model name | Planned deprecation date | Planned withdrawal date | Alternative foundation models |
|---|---|---|---|
|
|
|
|
|
There are no models that are planned for deprecation currently.
Withdrawn models
The following table lists the foundation models that were previously available from watsonx.ai, but are now withrawn.
| Foundation model name | API model ID | Deprecation date | Withdrawal date | Alternative foundation model |
|---|---|---|---|---|
| granite-13b-chat-v2 | ibm/granite-13b-chat-v2 |
4 November 2024 | 3 February 2025 | granite-3-8b-instruct |
| llama-3-8b-instruct | meta-llama/llama-3-8b-instruct |
2 December 2024 | 3 February 2025 | llama-3-2-11b-vision-instruct |
| llama-3-70b-instruct (Dallas, Frankfurt, London, and Tokyo data centers) |
meta-llama/llama-3-70b-instruct |
2 December 2024 | 3 February 2025 | llama-3-3-70b-instruct, llama-3-2-90b-vision-instruct |
| granite-7b-lab | ibm/granite-7b-lab |
7 October 2024 | 7 January 2025 | granite-3-8b-instruct |
| llama2-13b-dpo-v7 | mnci/llama2-13b-dpo-v7 |
4 November 2024 | 4 December 2024 | llama-3-1-8b-instruct |
| mt0-xxl-13b | bigscience/mt0-xxl |
4 November 2024 | 4 December 2024 | llama-3-1-8b-instruct, llama-3-2-11b-vision-instruct |
| llama3-llava-next-8b-hf | meta-llama/llama3-llava-next-8b-hf |
7 October 2024 | 7 November 2024 | llama-3-2-11b-vision-instruct |
| llama-2-70b-chat | meta-llama/llama-2-70b-chat |
26 August 2024 | 25 September 2024 | llama-3.1-70b-instruct |
| mixtral-8x7b-instruct-v01-q | ibm-mistralai/mixtral-8x7b-instruct-v01-q |
19 April 2024 | 30 August 2024 | mixtral-8x7b-instruct-v01 |
| merlinite-7b | ibm-mistralai/merlinite-7b |
22 July 2024 | 22 August 2024 | mixtral-8x7b-instruct-v01 |
| starcoder-15.5b | bigcode/starcoder |
15 February 2024 | 25 April 2024 | codellama-34b-instruct |
| mpt-7b-instruct2 | ibm/mpt-7b-instruct2 |
15 February 2024 | 21 March 2024 | mixtral-8x7b-instruct-v01-q |
| gpt-neox-20b | eleutherai/gpt-neox-20b |
15 February 2024 | 21 March 2024 | mixtral-8x7b-instruct-v01-q |
| granite-13b-chat-v1 | ibm/granite-13b-chat-v1 |
11 January 2024 | 11 April 2024 | granite-13b-chat-v2 |
| granite-13b-instruct-v1 | ibm/granite-13b-instruct-v1 |
11 January 2024 | 11 April 2024 | granite-13b-instruct-v2 |
What to do next
You must choose an alternative supported foundation model to use if any of the following saved resources submit input to a foundation model that is withdrawn:
- Prompt template asset
- Prompt session asset
- Notebook asset
For more information about working with saved prompt assets, see Saving your work.
For more information about how to change the foundation model that is inferenced from a notebook asset, see Inferencing a foundation model with a notebook.
Parent topic: Supported foundation models