4.1 Recommended Models

Data Science Agent works with large language models accessed through Oracle DBMS_CLOUD_AI and DBMS_CLOUD_AI_AGENT packages. The DBMS_CLOUD_AI package, with Select AI, supports the translation of natural language prompts to generate, run, explain SQL statements, and also enables RAG and natural language-based interactions, including chats with LLMs. For more information, see DBMS_CLOUD_AI Package and DBMS_CLOUD_AI_AGENT Package.

This table lists the recommended large language models and the scenarios in which each should be used.

Note:

Recommended models may change as providers update model availability, latency, pricing, and quality. Check the current list of supported models for your AI provider before creating a profile.

Table 4-1 Recommended Models

Provider	Tier	Large Language Model
OpenAI or OCI GenAI	Top	gpt-5.5
OpenAI or OCI GenAI	Cost-effective	gpt-5.4-mini
OCI GenAI	Top	xai.grok-4.3 Note: When using OCI Generative AI, use the provider and model identifiers exactly as documented for OCI GenAI. Some model identifiers may include the original model family or vendor name.
OCI GenAI	Cost-effective	xai.grok-4-1-fast-reasoning Note: When using OCI Generative AI, use the provider and model identifiers exactly as documented for OCI GenAI. Some model identifiers may include the original model family or vendor name.
Google	Top	gemini-3.5-flash
Google	Cost-effective	gemini-3-flash-preview
Anthropic	Top	claude-opus-4-8
Anthropic	Cost-effective	claude-sonnet-4-6

Explanation of tiers:

• Top: Represents the best state-of-the-art model from a specific provider. This tier is the strongest option in terms of quality, reliability, and precision.
• Cost-effective: Represents a good compromise between quality, cost, and speed. These models are typically faster and less expensive. But the trade-off is lower quality and reliability compared to the Top tier.

Profile Creation for GPT-5.5

To create an AI profile for GPT-5.5 through OpenAI, run the following script in a notebook:

DECLARE
    profile_name VARCHAR2(128) := 'OPENAI_GPT_5_5';
BEGIN
    dbms_cloud_ai.drop_profile(profile_name, TRUE);
    dbms_cloud_ai.create_profile(
        profile_name => profile_name,
        attributes => '{
            "credential_name": "OPENAI_CRED",
            "model": "gpt-5.5",
            "provider": "openai",
            "temperature": 1,
            "max_tokens": 8192
        }'
    );
END;
/

To create an AI profile for GPT 5.5 through Oracle Cloud Infrastructure (OCI), run the following script in a notebook:

DECLARE
    profile_name VARCHAR2(128) := 'OCI_GPT_5_5';
BEGIN
    dbms_cloud_ai.drop_profile(profile_name, TRUE);
    dbms_cloud_ai.create_profile(
        profile_name => profile_name,
        attributes => '{
            "credential_name": "OCI_CRED",
            "model": "openai.gpt-5.5",
            "provider": "oci",
            "temperature": 1,
            "max_tokens": 8192,
            "oci_compartment_id": "<your-dep-id>"
          }'
        );
    END;
/

Profile Creation for Grok 4.3

To create an AI profile for Grok 4.3 through Oracle Cloud Infrastructure (OCI), run the following script in a notebook:

DECLARE
    profile_name VARCHAR2(128) := 'OCI_GROK_4_3';
BEGIN
        dbms_cloud_ai.drop_profile(profile_name, TRUE);
        dbms_cloud_ai.create_profile(
            profile_name => profile_name,
            attributes => '{
                "credential_name": "OCI_CRED",
                "model": "xai.grok-4.3",
                "provider": "oci",
                "temperature": 1,
                "max_tokens": 8192,    
                "oci_compartment_id": "<your-dep-id>"
               }'
            );
    END;
/

Parameters:

• profile_name: Name of the AI profile. It must follow Oracle SQL identifier naming rules.
• credential_name: Name of the credential used to authenticate with the selected AI provider.
• model: Model identifier used by the selected provider.
• provider: AI provider for the profile, for example openai, oci, google, or anthropic.
• temperature: Recommended value for Data Science Agent examples: 1.
• max_tokens: Recommended value for these examples: 8192.

  Note:

  Data Science Agent profile inspection treats values below 4096 as not recommended.
• oci_compartment_id: Required for the OCI GenAI examples. Use the target compartment OCID or documented deployment/compartment identifier.

For more information, see Manage AI Profiles.