Skip to main content
Updated in 2026.12 The table provides an overview of the LLM providers supported by Cognigy.AI, detailing the standard models and their compatibility with Cognigy.AI features. You can also add a custom model that isn’t listed in the table. To do so, select the Custom Model parameter when creating a model and specify both the model type and name. For more information about adding a custom or standard model for a selected LLM provider, refer to the All LLM Providers page.
Models
Design-Time Features1AI Agent NodeConversation Analyzer8AI Enhanced OutputsLLM Prompt NodeAnswer ExtractionKnowledge SearchSentiment AnalysisNLU Embedding Model
cognigy-ai-logo Cognigy.AI
Platform-Provided LLMcheck-markx-markx-markx-markx-markx-markx-markx-markx-mark
azure Microsoft Azure OpenAI
gpt-5-52,7
gpt-5-42
gpt-5-4-mini2
gpt-5-4-nano2
gpt-5-22
gpt-5-12
gpt-52
gpt-5-nano2
gpt-5-mini2
gpt-5-chat-latest
gpt-4.1-nano
gpt-4.1-mini
gpt-4.1
gpt-4o-mini
gpt-4o		check-markcheck-markcheck-markcheck-markcheck-markcheck-markcheck-markcheck-markcheck-markx-markcheck-markx-mark
text-embedding-ada-002
text-embedding-3-small3
text-embedding-3-large3		x-markx-markx-markx-markx-markx-markx-markcheck-markx-markx-mark
open-ai OpenAI
gpt-5-52,7
gpt-5-42
gpt-5-4-mini2
gpt-5-4-nano2
gpt-5-22
gpt-5-12
gpt-52
gpt-5-nano2
gpt-5-mini2
gpt-5-chat-latest
gpt-4.1-nano
gpt-4.1-mini
gpt-4.1
gpt-4o-mini
gpt-4o		check-markcheck-markcheck-markcheck-markcheck-markcheck-markcheck-markcheck-markcheck-markx-markcheck-markx-mark
text-embedding-ada-002
text-embedding-3-small3
text-embedding-3-large3		x-markx-markx-markx-markx-markx-markx-markcheck-markx-markx-mark
openai-compatibleOpenAI-Compatible
OpenAI-compatible LLMsx-markcheck-markcheck-markcheck-markx-markcheck-markcheck-markcheck-markx-markx-mark
anthropic Anthropic
claude-sonnet-4-62
claude-sonnet-4-52
claude-sonnet-4-0		check-markcheck-markcheck-markcheck-markcheck-markcheck-markx-markcheck-markx-mark
claude-haiku-4-52x-markcheck-markcheck-markcheck-markx-markcheck-markcheck-markx-markx-markx-mark
google-gemini Google Gemini
gemini-2.5-pro2
gemini-2.5-flash2
gemini-2.5-flash-lite2
gemini-2.0-flash (deprecated)
gemini-2.0-flash-lite (deprecated)		x-markcheck-markcheck-markcheck-markx-markcheck-markcheck-markx-markx-markx-mark
gemini-embedding-001x-markx-markx-markx-markx-markx-markx-markcheck-markx-markx-mark
google-genai Google GenAI
gemini-3.1-pro-preview2
gemini-3-flash-preview2
gemini-3.5-flash2
gemini-3.1-flash-lite2
gemini-3.1-flash-lite-preview2 (deprecated)		x-markcheck-markx-markcheck-markcheck-markx-markx-markx-mark
alephalpha Aleph Alpha
luminous (deprecated)x-markx-markx-markx-markcheck-markx-markx-markx-mark
amazon-bedrock Amazon Bedrock
anthropic.claude-3-5-sonnet-20240620-v1:0 (deprecated)
amazon.nova-lite-v1:0 (deprecated)
amazon.nova-pro-v1:0 (deprecated)
amazon.nova-premier-v1:02
amazon.nova-2-lite-v1:0		x-markcheck-markx-markcheck-markcheck-markx-markx-markx-mark
amazon.titan-embed-text-v2:05x-markx-markx-markx-markx-markcheck-markx-markx-mark
amazon.nova-micro-v1:0 (deprecated)x-markx-markx-markcheck-markcheck-markx-markx-markx-mark
Converse API-compatible modelsx-markPartially supported6x-markx-markcheck-markx-markx-markx-mark
mistral Mistral AI
pixtral-12b-2409
mistral-large-latest4
mistral-medium-latest4
mistral-small-latest4
pixtral-large-latest4		x-markcheck-markx-markcheck-markcheck-markx-markx-markx-mark

​
More Information

1 Design-time features include Intent Sentence Generation, Flow Generation, Adaptive Card Generation, Lexicon Generation.
2 Reasoning models consume more tokens and may incur higher costs. The models are optimized for tasks that require complex problem-solving and logical reasoning. Before using these models in production, test token consumption in debug mode and use them with caution. To reduce costs, consider using a non-reasoning model such as gpt-5-chat-latest. For more information about reasoning models, refer to the Microsoft Azure OpenAI, OpenAI, and Google documentation.
Anthropic’s claude-sonnet-4-6 model doesn’t support assistant message prefilling. To keep your Flows compatible, ensure that the last transcript step before the LLM call is a user message. For example, add an Add Transcript Step Node before the LLM call and set the role to user.
3 For Knowledge AI, we recommend using text-embedding-ada-002. However, if you want to use text-embedding-3-small and text-embedding-3-large, make sure that you familiarize yourself with the restrictions of these models in Which Model to Choose?.
4 The *-latest suffix indicates that the model you select in Cognigy.AI points to the latest version of the model. For more information, read Anthropic’s or Mistral AI’s models documentation.
5 For Cognigy.AI 2025.10 and earlier versions, the option to select this model is hidden behind the FEATURE_ENABLE_AWS_BEDROCK_EMBEDDING_LLM_WHITELIST feature flag.
6 Note that some models from the Converse API might not support the AI Agent Node feature.
7 This model supports only the Responses API. When you select this model, the Responses API is selected by default, and the API Type field is locked. 8 The Conversation Analyzer uses the selected model to analyze session transcripts in Cognigy Insights. If no model is explicitly selected in Manage > Settings > Generative AI Settings, the Project’s default LLM is used. Any chat model that supports the AI Agent Node also supports the Conversation Analyzer.
Last modified on June 10, 2026