跳转至

Supported LLMs（支持的LLM）

Palantir AIP supports a wide range of LLMs (large language models) and text embedding models from leading providers, including xAI, OpenAI, Anthropic, Meta, and Google. Supported models are listed on this page and can be used across the Palantir platform to power AIP workflows, though availability may differ across enrollments (for instance, due to georestriction).

To use a specific model, an enrollment administrator must first enable the model family for use through Control Panel. Learn how to configure the selection of LLMs available for use on your enrollment.

Available LLMs

The following LLMs are supported for use with AIP, subject to enrollment availability.

Available text embedding models

Palantir AIP also supports the following text embedding models:

LLM availability prerequisites

AIP is model-agnostic and supports a diverse selection of models for LLM-powered use cases; for more information, refer to this list of all models available in AIP.

However, LLM selection and availability differs across enrollments based on certain prerequisites for a specific model to be available on an enrollment. These prerequisites determine whether a model family appears as enabled, disabled, or disallowed in Control Panel. Learn more about model states in the Model enablement interface.

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. Models awaiting legal acknowledgment appear in a disabled state.
  • 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 Claude 3 Sonnet were both only available in the US on release from each respective model provider before they were available in the EU, UK, and other regions. Review the model georestriction section for details. Models unavailable due to geographical restrictions appear in a disallowed state.
  • 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. Models requiring these reviews appear in a disallowed state.
  • 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.

LLM rate limits

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

LLM availability by geography

Some enrollments may have access to a limited set of models because of geographical restriction (or georestriction for short); georestriction for a certain region means that any AIP request to a LLM stays within the boundaries of that region. For example, if an enrollment is defined as EU geo-restricted, all LLM requests will be processed in the EU. Non-georestricted enrollments have access to the full set of Palantir-supported models.

The following table indicates the regional georestriction options for the various models supported by AIP. Note that the regional georestriction refers to the enrollment setup, not to the location of a specific user.

Model Provider Model US EU UK CA AU JP KSA IL2 IL4 IL5
xAI Grok-4 ✅
xAI Grok 4.1 Fast (Reasoning) ✅
xAI Grok 4.1 Fast (Non-Reasoning) ✅
Bedrock / Vertex / Anthropic Claude 4.5 Sonnet ✅ ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4.5 Haiku ✅ ✅ ✅ ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4.5 Opus ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4.6 Opus ✅ ✅ ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4.6 Sonnet ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4.7 Opus ✅ ✅ ✅ ✅ ✅
Vertex Gemini 2.5 Flash Lite ✅ ✅ ✅ ✅
Azure / OpenAI GPT-5.1 ✅ ✅ ✅
Azure / OpenAI GPT-5.1 Codex ✅
Azure / OpenAI GPT-5.1 Codex Max ✅
Azure / OpenAI GPT-5.1 Codex Mini ✅
Azure / OpenAI GPT-5-mini ✅ ✅
Azure / OpenAI GPT-5-nano ✅ ✅
Azure / OpenAI GPT-4.1 ✅ ✅ ✅ ✅ ✅
Azure / OpenAI GPT-4.1-mini ✅ ✅ ✅ ✅ ✅ ✅
Azure / OpenAI GPT-4.1-nano ✅ ✅
Azure / OpenAI ada002 ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Azure / OpenAI embedding3-large ✅ ✅ ✅ ✅ ✅ ✅
Azure / OpenAI embedding3-small ✅ ✅ ✅ ✅ ✅ ✅ ✅
Azure o4-mini ✅ ✅
Azure o3 ✅ ✅
Bedrock Llama4 16B Scout ✅
Bedrock Llama4 128B Maverick ✅
xAI Grok-3 ✅
xAI Grok-3 mini ✅
xAI Grok-Code-Fast-1 ✅
xAI Grok 4 Fast (Reasoning) ✅
xAI Grok 4 Fast (Non-Reasoning) ✅
Bedrock / Vertex / Anthropic Claude 4.1 Opus ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4 Sonnet ✅ ✅ ✅ ✅
Vertex / Anthropic Claude 4 Opus ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 3.7 Sonnet ✅ ✅ ✅ ✅ ✅ ✅
Bedrock Claude 3 Haiku ✅ ✅ ✅
Bedrock Claude 3.5 Haiku ✅ ✅
Bedrock Claude3.5 Sonnet v2 ✅ ✅
Bedrock Claude3.5 Sonnet ✅ ✅ ✅ ✅ ✅
Vertex Gemini 2.5 Pro ✅ ✅ ✅ ✅
Vertex Gemini 2.5 Flash ✅ ✅ ✅ ✅ ✅
Azure / OpenAI GPT-5 ✅ ✅
Azure / OpenAI GPT-5 Pro
Azure / OpenAI GPT-5 Codex ✅
Azure / OpenAI GPT-5.2 ✅
Azure / OpenAI GPT-5.2 Codex ✅
Azure / OpenAI GPT-5.3 Codex ✅
Azure / OpenAI GPT-5.4 ✅
Azure / OpenAI GPT-5.4 mini ✅
Azure / OpenAI GPT-5.4 nano ✅
Azure / OpenAI GPT-5.5 ✅ ✅
Azure / OpenAI GPT-4o ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Azure / OpenAI GPT-4o-mini ✅ ✅ ✅ ✅ ✅ ✅ ✅
Azure o3-mini ✅ ✅ ✅ ✅ ✅
Azure o1 ✅ ✅
Open source (Palantir-hosted) Llama3.1 8B ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Open source (Palantir-hosted) Llama3.3 70B ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Open source (Palantir-hosted) Llama3.3 Nemotron Super 49b v1.5 ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Open source (Palantir-hosted) Llama3.2 NV EmbedQA 1B v2 ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Open source (Palantir-hosted) Mixtral 8x7B ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Open source (Palantir-hosted) Document Information Extraction ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅

Bring your own model (LLM)

Bring your own model is a capability that provides first-class support for customers that would like to connect their own LLMs or accounts to use in AIP with all Palantir developer products - AIP Logic, Pipeline Builder, Chatbot Studio, Workshop, etc.

Review the bring your own model documentation to learn how to register models for use in AIP.

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

The "OpenAI" name and the “GPT” brands are property of OpenAI.

All third-party trademarks (including logos and icons) referenced remain the property of their respective owners. No affiliation or endorsement is implied.

中文翻译

支持的LLM

Palantir AIP 支持来自领先提供商（包括 xAI、OpenAI、Anthropic、Meta 和 Google）的多种 LLM（大语言模型，large language model）和文本嵌入模型（text embedding model）。本页面列出了支持的模型，这些模型可在 Palantir 平台中使用，为 AIP 工作流提供支持，但不同注册环境（enrollment）的可用性可能有所不同（例如，由于地理限制）。

要使用特定模型，注册管理员必须首先通过控制面板（Control Panel）启用该模型系列。了解如何配置可供注册环境使用的 LLM 选择。

可用的 LLM

以下 LLM 受支持与 AIP 配合使用，但需满足注册环境可用性条件。

可用的文本嵌入模型

Palantir AIP 还支持以下文本嵌入模型（text embedding model）：

LLM 可用性前提条件

AIP 与模型无关（model-agnostic），支持多种模型用于 LLM 驱动的用例；更多信息请参考此列表，了解 AIP 中所有可用的模型。

然而，LLM 的选择和可用性在不同注册环境之间有所不同，这取决于特定模型在注册环境中可用的某些前提条件。这些前提条件决定了模型系列在控制面板中显示为已启用、已禁用或不允许。了解更多关于模型启用界面中的模型状态。

标准如下：

  • 模型已与 AIP 集成： Palantir 旨在支持业界最新的旗舰模型，并积极根据模型发布和更新进行支持开发。
  • 已按要求提供法律确认： 注册管理员必须接受提供商的法律要求和使用条款，才能启用某些模型。这通常可以在控制面板的模型启用选项卡下完成。等待法律确认的模型显示为已禁用状态。
  • 已在注册环境中启用 AIP 以使用 LLM： 要在 AIP Logic、Transforms、Functions 和 Pipeline Builder 等产品中使用，必须为目标用户组启用 AIP 自定义工作流功能的权限。
  • 区域可用性兼容性（适用于外部提供商模型）： 对于 GPT、Claude 和 Gemini 等模型，如果您处于地理限制的注册环境中，可能需要考虑区域可用性。例如，GPT4o 和 Claude 3 Sonnet 在欧盟、英国和其他地区可用之前，最初仅在美国可用。详情请查看模型地理限制部分。由于地理限制而不可用的模型显示为不允许状态。
  • 已进行额外审查（适用于某些 Palantir 提供的模型）： 开源模型（如 Llama 和 Mixtral）可能需要额外的 Palantir 工程审查以支持您的环境。需要这些审查的模型显示为不允许状态。
  • 与特定 AIP 前端产品集成的时间充足： 新的 LLM 需要时间才能在所有 AIP 产品上得到完全支持（例如，在 AIP Logic 和 Pipeline Builder 的"使用 LLM 节点"功能中）。
  • 风险考量（适用于实验性模型）： 由于实验性模型可能中断或需要手动迁移到较新模型，我们限制其推广，客户可能需要在启用使用前确认这一点。"实验性"一词由模型提供商描述，不适用于生产用途。

LLM 速率限制

有关 LLM 速率限制的信息，请查看 LLM 容量管理文档。

按地理区域的 LLM 可用性

某些注册环境可能由于地理限制（georestriction）而只能访问有限的模型集；特定区域的地理限制意味着任何对 LLM 的 AIP 请求都保持在该区域边界内。例如，如果注册环境被定义为欧盟地理限制，所有 LLM 请求将在欧盟处理。非地理限制的注册环境可以访问 Palantir 支持的完整模型集。

下表显示了 AIP 支持的各种模型的区域地理限制选项。请注意，区域地理限制指的是注册环境设置，而非特定用户的位置。

模型提供商 模型 美国 欧盟 英国 加拿大 澳大利亚 日本 沙特阿拉伯 IL2 IL4 IL5
xAI Grok-4 ✅
xAI Grok 4.1 Fast (Reasoning) ✅
xAI Grok 4.1 Fast (Non-Reasoning) ✅
Bedrock / Vertex / Anthropic Claude 4.5 Sonnet ✅ ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4.5 Haiku ✅ ✅ ✅ ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4.5 Opus ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4.6 Opus ✅ ✅ ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4.6 Sonnet ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4.7 Opus ✅ ✅ ✅ ✅ ✅
Vertex Gemini 2.5 Flash Lite ✅ ✅ ✅ ✅
Azure / OpenAI GPT-5.1 ✅ ✅ ✅
Azure / OpenAI GPT-5.1 Codex ✅
Azure / OpenAI GPT-5.1 Codex Max ✅
Azure / OpenAI GPT-5.1 Codex Mini ✅
Azure / OpenAI GPT-5-mini ✅ ✅
Azure / OpenAI GPT-5-nano ✅ ✅
Azure / OpenAI GPT-4.1 ✅ ✅ ✅ ✅ ✅
Azure / OpenAI GPT-4.1-mini ✅ ✅ ✅ ✅ ✅ ✅
Azure / OpenAI GPT-4.1-nano ✅ ✅
Azure / OpenAI ada002 ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Azure / OpenAI embedding3-large ✅ ✅ ✅ ✅ ✅ ✅
Azure / OpenAI embedding3-small ✅ ✅ ✅ ✅ ✅ ✅ ✅
Azure o4-mini ✅ ✅
Azure o3 ✅ ✅
Bedrock Llama4 16B Scout ✅
Bedrock Llama4 128B Maverick ✅
xAI Grok-3 ✅
xAI Grok-3 mini ✅
xAI Grok-Code-Fast-1 ✅
xAI Grok 4 Fast (Reasoning) ✅
xAI Grok 4 Fast (Non-Reasoning) ✅
Bedrock / Vertex / Anthropic Claude 4.1 Opus ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 4 Sonnet ✅ ✅ ✅ ✅
Vertex / Anthropic Claude 4 Opus ✅ ✅ ✅ ✅
Bedrock / Vertex / Anthropic Claude 3.7 Sonnet ✅ ✅ ✅ ✅ ✅ ✅
Bedrock Claude 3 Haiku ✅ ✅ ✅
Bedrock Claude 3.5 Haiku ✅ ✅
Bedrock Claude3.5 Sonnet v2 ✅ ✅
Bedrock Claude3.5 Sonnet ✅ ✅ ✅ ✅ ✅
Vertex Gemini 2.5 Pro ✅ ✅ ✅ ✅
Vertex Gemini 2.5 Flash ✅ ✅ ✅ ✅ ✅
Azure / OpenAI GPT-5 ✅ ✅
Azure / OpenAI GPT-5 Pro
Azure / OpenAI GPT-5 Codex ✅
Azure / OpenAI GPT-5.2 ✅
Azure / OpenAI GPT-5.2 Codex ✅
Azure / OpenAI GPT-5.3 Codex ✅
Azure / OpenAI GPT-5.4 ✅
Azure / OpenAI GPT-5.4 mini ✅
Azure / OpenAI GPT-5.4 nano ✅
Azure / OpenAI GPT-5.5 ✅ ✅
Azure / OpenAI GPT-4o ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Azure / OpenAI GPT-4o-mini ✅ ✅ ✅ ✅ ✅ ✅ ✅
Azure o3-mini ✅ ✅ ✅ ✅ ✅
Azure o1 ✅ ✅
开源（Palantir 托管） Llama3.1 8B ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
开源（Palantir 托管） Llama3.3 70B ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
开源（Palantir 托管） Llama3.3 Nemotron Super 49b v1.5 ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
开源（Palantir 托管） Llama3.2 NV EmbedQA 1B v2 ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
开源（Palantir 托管） Mixtral 8x7B ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
开源（Palantir 托管） 文档信息提取 ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅

自带模型（LLM）

自带模型（Bring your own model）是一项功能，为希望连接自己的 LLM 或账户以在 AIP 中使用的客户提供一流支持，适用于所有 Palantir 开发者产品——AIP Logic、Pipeline Builder、Chatbot Studio、Workshop 等。

请查看自带模型文档，了解如何注册模型以在 AIP 中使用。

注意：AIP 功能可用性可能发生变化，且不同客户之间可能存在差异。

"OpenAI"名称和"GPT"品牌均为 OpenAI 的财产。

所有第三方商标（包括引用的徽标和图标）仍归其各自所有者所有。不暗示任何隶属关系或认可。