(Optional) Using your own watsonx.ai account with the Content Assistant
You can purchase a watsonx.ai license in order to use your own
watsonx.ai account with the Content Assistant.
You have the following advantages when you use your own watsonx.ai account
with the Content Assistant:
- You can use any LLM that is supported on watsonx.ai. For the list of supported models, see Content Assistant supported foundation models.
- You can fine-tune a supported LLM and use the custom trained LLM with the Content Assistant.
- You can use any embedding model that is available in watsonx.ai. For the list of supported models, see Content Assistant supported foundation models.
- You can increase the number of GenAI queue sweep workers to improve the performance and throughput for summary generation and vector indexing.
Content Assistant supported foundation models
The following table lists the large language models supported by the Content Assistant:
| Model name | Dallas | Frankfurt |
|---|---|---|
| granite-4-h-small | ✓ | ✓ |
| llama-3-3-70b-instruct | ✓ | ✓ |
| llama-4-maverick-17b-128e-instruct-fp8 | ✓ | ✓ |
| mistral-medium-2505 | ✓ | ✓ |
| gpt-oss-120b | ✓ |
Note: For more information about the availability of a supported model across a data center, see
Regional availability of foundation models.
The following table lists the embedding models supported by the Content Assistant:
| Model name | Dallas | Frankfurt |
|---|---|---|
| slate-125m-english-rtrvr-v2 | ✓ | ✓ |
| granite-embedding-278m-multilingual | ✓ | ✓ |
| intfloat/multilingual-e5-large | ✓ | ✓ |