All LLM Providers

To add a standard or custom model, select a large language model (LLM) provider integrated with Cognigy.AI:

• Platform-Provided LLM1

  ---

  Cognigy.AI provides a GPT-based LLM for setting up and testing design-time features.

• Azure OpenAI

  ---

  Add credentials for the predefined models, such as gpt-4o, gpt-4o-mini, and text-embedding models, or a custom model based on an Azure OpenAI model.

• OpenAI

  ---

  Add credentials for the predefined models, such as gpt-4o, gpt-4o-mini, and text-embedding models, or add a custom model based on an OpenAI model.

• OpenAI-Compatible LLMs

  ---

  Add credentials for models from any providers that adhere to the OpenAI API standards, including HuggingFace, DeepSeek, xAI, Fireworks AI and others.

• Anthropic

  ---

  Add credentials for the predefined models such as claude-3-opus, claude-3-sonnet, claude-3-opus, or add a custom model based on an Anthropic model.

• Google Vertex

  ---

  Add credentials for the predefined model text-bison-001 (Bard) or add a custom model based on a model from the Vertex AI family.

• Google Gemini

  ---

  Add credentials for the predefined model, such as gemini-2.0-flash and gemini-2.0-flash-lite, or add a custom model based on a model from the Gemini family.

• Aleph Alpha

  ---

  Add credentials for the predefined models such as luminous and luminous-embedding-128 or add a custom model based on an Aleph Alpha model.

• Amazon Bedrock

  ---

  Add credentials for the predefined models or add a custom model based on any Amazon Bedrock model that supports the Converse API.

• Mistral AI

  ---

  Add credentials for the predefined models, such as mistral-large-2411 and pixtral-large-2503, or add a custom model based on a Mistral AI model.

• Cognigy Nexus LLM

  ---

  Cognigy Nexus LLM is a proprietary LLM, provided and hosted by Cognigy, optimized for AI-driven customer service.

---

1. The Platform-Provided LLM is available only to customers with SaaS installations. ↩