LLMs and Databases¶

SkyDeck.ai connects to a range of large language model (LLM) providers, as well as to your own databases. You add each one in the Control Center under Integrations: choose the service, give the integration a name, and paste your credentials (for most providers this is simply the provider's API key). SkyDeck.ai validates the credentials in the background, and once they're accepted, that provider's models become available for your members to select in GenStudio.

The pages in this section provide step-by-step setup instructions for OpenAI, Anthropic, Google Gemini, Vertex AI, Groq, Mistral, Together AI, Perplexity, xAI, and HuggingFace (for your own hosted inference endpoints).

Beyond the providers with native integrations (OpenAI, Anthropic, and Google Gemini), SkyDeck.ai reaches the other services — including Vertex AI, Groq, Mistral, Together AI, Perplexity, and xAI — through an OpenAI-compatible layer (LiteLLM). This is what lets the platform support a broad and growing range of models: the specific models offered for each provider are maintained in SkyDeck.ai's model catalog and updated over time, so new models generally become available without any change to your integration. (Google Gemini and Vertex AI are separate integrations — Gemini uses a direct API key, while Vertex AI uses a Google Cloud service account.)

For databases, SkyDeck.ai supports PostgreSQL, including Amazon Redshift, which connects over the PostgreSQL protocol.

Anthropic Integration Database Integration Gemini Integration Groq Integration HuggingFace Integration Mistral Integration OpenAI Integration Perplexity Integration Together AI Integration Vertex AI Integration xAI Integration