Enable AIP features

Palantir AIP (Artificial Intelligence Platform) is enabled by default in new enrollments. Enrollments that began prior to 2024 may need to manually turn on access to AIP features in Control Panel. Your AIP configuration can be managed in Control Panel > AIP settings if you are an enrollment administrator.

Note that enabling AIP may incur additional compute usage.

Learn more about AIP, including a list of supported models and developer capabilities.

AIP and capabilities for custom workflows

AIP usage on the Palantir platform is governed by two levels of permissions:

AIP and core assistant features: Turns on AIP, AIP Assist, AIP Threads, and associated assistant features in Code Repositories, Pipeline Builder, and Workshop.

AIP capabilities for custom workflows: With AIP enabled, platform administrators can enable an additional layer of capabilities to empower developers and application builders to create custom AIP workflows and grant users the necessary permissions to use these custom AIP workflows. Refer to the following table for capabilities that are unlocked when permission is granted.

Platform administrators can choose to enable usage for Everyone or given User Groups, or restrict usage by selecting Nobody.

Note that certain apps, such as AIP Logic, may need to first be enabled in Control Panel > Application access before it can be used.

Enable LLMs

Enabling specific LLMs is performed separately after general AIP enablement and can be managed by enrollment administrators under the Model enablement tab within the AIP settings extension of Control Panel.

Enrollment administrators may view and manage the available models for use within AIP, which may differ across enrollments. View a list of all supported models. Models are grouped according to their legal requirements and terms of use, and groups can be individually enabled. Disabling a model group will break workflows that rely on a model in that specific group.

Model groups may be currently disallowed if the legal requirements for use have not been satisfied. In this case, an enrollment administrator may need to first accept the relevant terms and conditions for the specific model. Note that certain LLM groups may require manual configuration by your Palantir representative to use.

Experimental models

Usage of experimental models can be enabled and disabled by enrollment administrators. For an experimental model to be visible for use in workflows, the Enable experimental models toggle must be enabled as well as the model family to which the experimental model belongs.

LLM availability

AIP is model-agnostic and supports a diverse selection of models for LLM-powered use cases. However, LLM selection and availability differs across enrollments and there are a few prerequisites for a specific model to be available on an enrollment. The criteria are listed below:

• Model has been integrated with AIP: Palantir aims to support the latest flagship models in the industry and is actively developing support in line with model releases and updates.
• Legal acknowledgment has been given where required: Enrollment administrators must accept the legal requirements and terms of use of a provider to have certain models enabled. This can usually be done in Control Panel under the Model enablement tab.
• AIP has been enabled on an enrollment to use an LLM: For usage in products such as AIP Logic, Transforms, Functions, and Pipeline Builder, the permissions for AIP capabilities for custom workflows must be enabled for intended user groups.
• Regional availability compatibility (for external provider models): For models like GPT, Claude, and Gemini, you may need to consider regional availability if you are on a geography-restricted enrollment. For example, GPT4o and Claude3 Sonnet were both only available in the US on release before they were available in the EU, UK, and other regions. Review the model availability section for details.
• Additional reviews have been conducted (for certain Palantir-provided models): Open-source models, such as Llama and Mixtral, may require an additional Palantir engineering review to support your environment.
• Sufficient time to integration with a specific AIP frontend product: New LLMs take time to be fully supported on all AIP products (for example, in AIP Logic and in Pipeline Builder's use LLM node feature).
• Risk consideration (for experimental models): As experimental models might break or require a manual migration to a newer model, we limit their rollout and customers may be required to acknowledge the same before usage is enabled. The term "experimental" is as described by the model provider and not intended for operational usage.

Model availability on AIP related to geography

Some enrollments are geographically-restricted in that any AIP request to a LLM stays within the boundaries of a certain region. For example, if an enrollment is defined as EU geo-restricted, all requests will be processed in the EU.

Model regional availability refers to the enrollment setup, not to the location of a specific user. Review the following table:

LLM rate limits

For information on LLM rate limits, review the documentation on LLM capacity management.

---

Note: AIP feature availability is subject to change and may differ between customers.