Skip to main content
Parlé gives your organization access to leading AI models from four providers: Anthropic, OpenAI, Google Gemini, and Azure AI Foundry. Each provider brings distinct strengths — from long-context document reasoning to fast, cost-efficient summarization — and you can mix and match models across your projects to fit the nature of each engagement. Org admins control which models are enabled for each project, so you can align model access with budget and use-case requirements.
Context window figures in the tables below are approximate and based on publicly available provider documentation. Actual limits may vary by model version or provider configuration. Check your provider’s documentation for guaranteed limits.

​
Anthropic

Anthropic’s Claude models excel at nuanced instruction-following, long-document analysis, and professional writing tasks — capabilities that map well to legal drafting, contract review, and detailed client memoranda.

​
OpenAI

OpenAI’s GPT-4o family covers a broad range of workloads, from multimodal analysis to structured data extraction, while o1 is purpose-built for deep reasoning tasks that benefit from extended chain-of-thought processing.

​
Google Gemini

Google’s Gemini 1.5 models offer some of the largest context windows available, making them a strong choice when you need to load entire contracts, transcripts, or lengthy financial disclosures into a single conversation.

​
Azure AI Foundry

Azure AI Foundry delivers the same OpenAI models hosted within Microsoft’s Azure infrastructure. This option suits organizations that have existing Azure agreements, need data residency in specific Azure regions, or operate under compliance frameworks that require processing within a controlled cloud tenant.
Running your own deployment in your Azure tenant requires the Business Elite plan and above. This does not affect Parlé Managed models, which remain available on every plan.
For document-heavy legal or financial work — such as reviewing lengthy contracts, regulatory filings, or audit workpapers — Claude 3.5 Sonnet and Gemini 1.5 Pro handle long context particularly well and are worth setting as the default for those project types.
Model availability may change as providers release new versions or deprecate older ones. Parlé updates the model list regularly to reflect current provider offerings. Check Org settings → Models for the live list of models available to your org.