ContractRabbit Docs
Admin

LLM Models

Supported AI model providers, model options, regional availability, BYOK, and model selection settings.

Overview

Workspace admins can configure AI model selection in Admin > Settings > AI Models where the workspace plan allows it. Model availability depends on the workspace plan, deployment region, provider availability, customer credentials, and customer agreement.

ContractRabbit separates model selection by use case:

Use caseWhat it powers
AgentContract Q&A, tool use, drafting assistance, review workflows, and interactive analysis.
Knowledge extractionDocument metadata extraction, clause classification, field extraction, and structured contract data generation.
EmbeddingsSemantic search, retrieval, clustering, matching, and related knowledge workflows where configured.

Region support summary

RegionStandard postureTypical providers
United StatesStandard managed production configuration.Google Gemini / Vertex AI, OpenAI, Voyage for embeddings where configured.
European Union / EEAEnterprise-scoped regional configuration where available.Google Gemini / Vertex AI regional configuration, OpenAI EU data residency configuration where supported, Voyage only if provider terms and endpoint configuration satisfy the customer requirement.
ChinaApproved enterprise configuration only.DeepSeek and Qwen / DashScope.

EU/EEA, China, and other regional requirements should be confirmed during procurement because storage, processing, backups, support access, provider routing, and fallback behavior may all be in scope.

United States models

ProviderTypical modelUse caseNotes
Google Gemini / Vertex AIGemini 3.1 Flash LiteAgentDefault managed agent model.
Google Gemini / Vertex AIGemini 2.5 Flash LiteKnowledge extractionDefault managed extraction model.
Google Gemini / Vertex AIGemini 3 FlashAgent, knowledge extractionHigher-capability Gemini option where enabled.
Google Gemini / Vertex AIGemini 2.5 FlashAgent, knowledge extractionGeneral-purpose Gemini option.
Google Gemini / Vertex AIGemini 2.0 FlashAgent, knowledge extractionGeneral-purpose Gemini option.
OpenAIGPT-5 MiniAgent, knowledge extractionTypical OpenAI agent option and summary/document-generation option.
OpenAIGPT-5 NanoKnowledge extractionLower-cost OpenAI extraction option.
OpenAIGPT-5Agent, knowledge extractionHigher-capability OpenAI option where enabled.
VoyageEmbedding modelsEmbeddingsUsed for retrieval and semantic search workflows where configured.

European Union / EEA models

EU/EEA deployments require approved regional configuration. The model families below are typical enterprise options when the provider, model, endpoint, and retention terms support the customer's requirements.

ProviderTypical modelUse caseEU deployment notes
Google Gemini / Vertex AIGemini 3.1 Flash LiteAgentRequires approved regional Vertex/Gemini configuration and model availability.
Google Gemini / Vertex AIGemini 2.5 Flash LiteKnowledge extractionRequires approved regional Vertex/Gemini configuration and model availability.
Google Gemini / Vertex AIGemini 3 FlashAgent, knowledge extractionAvailable only where the selected regional endpoint supports the model.
Google Gemini / Vertex AIGemini 2.5 FlashAgent, knowledge extractionAvailable only where the selected regional endpoint supports the model.
OpenAIGPT-5 MiniAgent, knowledge extractionRequires approved OpenAI EU data residency configuration where supported.
OpenAIGPT-5 NanoKnowledge extractionRequires approved OpenAI EU data residency configuration where supported.
OpenAIGPT-5Agent, knowledge extractionRequires approved OpenAI EU data residency configuration where supported.
VoyageEmbedding modelsEmbeddingsAvailable only if provider terms and endpoint configuration satisfy the residency requirement.

For EU/EEA-restricted workspaces, model routing and fallback behavior are governed by the approved provider and region set in the applicable enterprise agreement or deployment plan.

China models

China-region model options are available only for approved enterprise deployments.

ProviderTypical modelUse caseNotes
DeepSeekDeepSeek V4 ProAgentChina-region agent option for approved deployments.
DeepSeekDeepSeek V4 FlashAgent, knowledge extractionChina-region extraction default for approved deployments.
Qwen / DashScopeQwen 3.6 PlusAgentChina-region agent alternate for approved deployments.
Qwen / DashScopeQwen 3.5 PlusAgent, knowledge extractionChina-region extraction alternate for approved deployments.

China-region model use requires approved provider credentials, endpoint configuration, and enterprise review. Full-platform China residency requires a separate deployment review for hosting, storage, network, AI providers, transfers, backups, and support access.

BYOK and provider credentials

Bring your own key lets paid workspaces use customer-managed provider credentials where supported.

ProviderBYOK supportNotes
GoogleSupported where plan and deployment allow it.Customer is responsible for provider account configuration and applicable provider terms.
OpenAISupported where plan and deployment allow it.Customer is responsible for provider account configuration, data controls, and applicable provider terms.
DeepSeekEnterprise-scoped.Available only for approved China-region deployments.
Qwen / DashScopeEnterprise-scoped.Available only for approved China-region deployments.

Model selection controls

ControlDescription
Provider selectionChoose the approved provider for agent and extraction workloads.
Use-case model selectionSelect separate models for agent workflows and knowledge extraction workflows.
AI Unit impactCompare model cost impact through normalized AI Units instead of raw provider token pricing.
Credential modeUse ContractRabbit-managed credentials or customer-managed credentials where the plan allows it.
Regional restrictionsEnterprise workspaces can define approved provider and region sets in the applicable agreement and deployment plan.

On this page