> ## Documentation Index
> Fetch the complete documentation index at: https://docs-classic.cognigy.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Model Support by Feature
> Explore LLM providers and models supported by Cognigy, including feature compatibility, standard and custom model options.
[Updated in 2026.23](https://docs-classic.cognigy.com/release-notes/2026.23.md)
The table provides an overview of the LLM providers supported by Cognigy, detailing the standard models and their compatibility with Cognigy 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](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/all-providers.md) page.
| Models | Design-Time Features[1](#footnote1) | AI Agent Node | Conversation Analyzer[8](#footnote8) | AI Enhanced Outputs | LLM Prompt Node | Answer Extraction | Knowledge Search | Sentiment Analysis | NLU Embedding Model |
| - | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: |
|  **[Cognigy](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/generative-ai.md#design-time-generative-ai-features)** | | | | | | | | | |
| Platform-Provided LLM |  |  |  |  |  |  |  |  |  |
|  **[Microsoft Azure OpenAI](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/microsoft-azure-openai.md)** | | | | | | | | | |
| `gpt-5-6-sol`[7](#footnote7),[11](#footnote11) `gpt-5-6-terra`[7](#footnote7),[11](#footnote11) `gpt-5-6-luna`[7](#footnote7),[11](#footnote11) `gpt-6-sol`[7](#footnote7),[11](#footnote11) `gpt-6-luna`[7](#footnote7),[11](#footnote11) `gpt-6-1-sol`[7](#footnote7),[11](#footnote11) |  |  |  |  |  |  |  |  |  |
| `gpt-5-5`[2](#footnote2),[7](#footnote7),[11](#footnote11) `gpt-5-4`[2](#footnote2),[11](#footnote11) `gpt-5-4-mini`[2](#footnote2),[11](#footnote11) `gpt-5-4-nano`[2](#footnote2),[11](#footnote11) `gpt-5-2`[2](#footnote2),[11](#footnote11) `gpt-5-1`[2](#footnote2),[11](#footnote11) `gpt-5`[2](#footnote2) `gpt-5-nano`[2](#footnote2) ([deprecated](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models)) `gpt-5-mini`[2](#footnote2) ([deprecated](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models)) `gpt-4.1-nano` ([deprecated](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models)) `gpt-4.1-mini` ([deprecated](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models)) `gpt-4.1` ([deprecated](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models)) `gpt-4o-mini` ([deprecated](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models)) `gpt-4o` ([deprecated](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models)) |  |  |  |  |  |  |  |  |  |
| `text-embedding-ada-002` `text-embedding-3-small`[3](#footnote3) `text-embedding-3-large`[3](#footnote3) |  |  |  |  |  |  |  |  |  |
|  **[OpenAI](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/openai.md)** | | | | | | | | | |
| `gpt-5-6-sol`[7](#footnote7),[11](#footnote11) `gpt-5-6-terra`[7](#footnote7),[11](#footnote11) `gpt-5-6-luna`[7](#footnote7),[11](#footnote11) `gpt-6-sol`[7](#footnote7),[11](#footnote11) `gpt-6-luna`[7](#footnote7),[11](#footnote11) `gpt-6-1-sol`[7](#footnote7),[11](#footnote11) |  |  |  |  |  |  |  |  |  |
| `gpt-5-5`[2](#footnote2),[11](#footnote11) `gpt-5-4`[2](#footnote2),[11](#footnote11) `gpt-5-4-mini`[2](#footnote2),[11](#footnote11) `gpt-5-4-nano`[2](#footnote2),[11](#footnote11) `gpt-5-2`[2](#footnote2),[11](#footnote11) `gpt-5-1`[2](#footnote2),[11](#footnote11) `gpt-5` ([deprecated](https://developers.openai.com/api/docs/deprecations))[2](#footnote2) `gpt-5-nano` ([deprecated](https://developers.openai.com/api/docs/deprecations))[2](#footnote2) `gpt-5-mini` ([deprecated](https://developers.openai.com/api/docs/deprecations))[2](#footnote2) `gpt-4.1-mini` ([deprecated](https://developers.openai.com/api/docs/deprecations)) `gpt-4.1` ([deprecated](https://developers.openai.com/api/docs/deprecations)) `gpt-4o-mini` `gpt-4o` |  |  |  |  |  |  |  |  |  |
| `text-embedding-ada-002` `text-embedding-3-small`[3](#footnote3) `text-embedding-3-large`[3](#footnote3) |  |  |  |  |  |  |  |  |  |
| **[OpenAI-Compatible](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/openai-compatible.md)** | | | | | | | | | |
| OpenAI-compatible LLMs |  |  |  |  |  |  |  |  |  |
|  **[Anthropic](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/anthropic.md)** | | | | | | | | | |
| `claude-sonnet-5`[2](#footnote2),[9](#footnote9) `claude-sonnet-5-5`[2](#footnote2),[9](#footnote9) `claude-haiku-5-5`[2](#footnote2),[9](#footnote9) `claude-opus-4-7`[2](#footnote2),[9](#footnote9) `claude-opus-4-8`[2](#footnote2),[9](#footnote9) `claude-opus-5`[2](#footnote2),[9](#footnote9) `claude-opus-5-5`[2](#footnote2),[9](#footnote9) |  |  |  |  |  |  |  |  |  |
| `claude-sonnet-4-6`[2](#footnote2) |  |  |  |  |  |  |  |  |  |
| `claude-sonnet-4-5` ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations))[2](#footnote2) |  |  |  |  |  |  |  |  |  |
| `claude-haiku-4-5`[2](#footnote2) |  |  |  |  |  |  |  |  |  |
|  **[Google Gemini](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/google-gemini.md)** | | | | | | | | | |
| `gemini-2.5-pro` ([deprecated](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable))[2](#footnote2) `gemini-2.5-flash`[2](#footnote2) `gemini-2.5-flash-lite`[2](#footnote2),[10](#footnote10) ([deprecated](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable)) `gemini-2.0-flash` ([deprecated](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable)) |  |  |  |  |  |  |  |  |  |
| `gemini-embedding-001` |  |  |  |  |  |  |  |  |  |
|  **[Google GenAI](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/google-genai.md)** | | | | | | | | | |
| `gemini-3.1-pro-preview`[2](#footnote2) `gemini-3-flash-preview`[2](#footnote2) `gemini-3.5-flash`[2](#footnote2) `gemini-3.1-flash-lite`[2](#footnote2) |  |  |  |  |  |  |  |  |  |
| `gemini-3.6-flash` ([deprecated](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions))[2](#footnote2) `gemini-3.7-flash` ([deprecated](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions))[2](#footnote2) `gemini-3.8-flash`[2](#footnote2) |  |  |  |  |  |  |  |  |  |
| `gemini-3.5-flash-lite`[2](#footnote2),[10](#footnote10) |  |  |  |  |  |  |  |  |  |
| `gemini-embedding-2` |  |  |  |  |  |  |  |  |  |
|  **[Aleph Alpha](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/aleph-alpha.md)** | | | | | | | | | |
| `luminous` ([deprecated](https://docs.aleph-alpha.com)) |  |  |  |  |  |  |  |  |  |
|  **[Amazon Bedrock](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/amazon-bedrock.md)** | | | | | | | | | |
| `anthropic.claude-3-5-sonnet-20240620-v1:0` ([deprecated](https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle.html)) `amazon.nova-lite-v1:0` |  |  |  |  |  |  |  |  |  |
| `amazon.nova-pro-v1:0` `amazon.nova-2-lite-v1:0` |  |  |  |  |  |  |  |  |  |
| `amazon.titan-embed-text-v2:0`[5](#footnote5) |  |  |  |  |  |  |  |  |  |
| `amazon.nova-micro-v1:0` |  |  |  |  |  |  |  |  |  |
| [Converse API](https://docs.aws.amazon.com/bedrock/latest/userguide/models-features.html)-compatible models |  | Partially supported[6](#footnote6) |  |  |  |  |  |  |  |
|  **[Mistral AI](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/mistral.md)** | | | | | | | | | |
| `mistral-large-latest`[4](#footnote4) `mistral-medium-latest` ([deprecated](https://docs.mistral.ai/models/overview#legacy-models))[4](#footnote4) `mistral-small-latest`[4](#footnote4) `ministral-14b-latest`[4](#footnote4) `ministral-8b-latest`[4](#footnote4) `ministral-3b-latest`[4](#footnote4) |  |  |  |  |  |  |  |  |  |
## More Information
* [Overview](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/llms.md)
* [All LLM Providers](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/all-providers.md)
* [Other LLM Operations](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/other-operations.md)
***
[Design-time
features](https://docs-classic.cognigy.com/ai/agents/develop/gen-ai-and-llms/generative-ai.md#design-time-generative-ai-features)
include Intent Sentence Generation, Flow Generation, Adaptive Card Generation,
Lexicon Generation.
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](https://docs-classic.cognigy.com/ai/agents/test/interaction-panel/chat.md#debug-mode) and use them with caution. To reduce costs, consider using a non-reasoning model. For more information about reasoning models, refer to the [Microsoft Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning), [OpenAI](https://platform.openai.com/docs/guides/reasoning/advice-on-prompting), and [Google](https://cloud.google.com/vertex-ai/generative-ai/docs/models) documentation.
Anthropic's `claude-sonnet-4-6` model doesn't support [assistant message prefilling](https://platform.claude.com/docs/en/about-claude/models/migration-guide#breaking-changes-3).
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](https://docs-classic.cognigy.com/ai/agents/develop/node-reference/service/add-transcript-step.md) before the LLM call and set the role to `user`.
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?](https://docs-classic.cognigy.com/ai/agents/develop/knowledge-ai/overview).
The `*-latest` suffix indicates that the model you
select in Cognigy points to the latest version of the model. For more
information, read
[Anthropic's](https://docs.anthropic.com/en/docs/about-claude/models/overview)
or [Mistral
AI's](https://docs.mistral.ai/getting-started/models/models_overview/) models
documentation.
For Cognigy 2025.10 and earlier versions, the
option to select this model is hidden behind the
`FEATURE_ENABLE_AWS_BEDROCK_EMBEDDING_LLM_WHITELIST` feature flag.
Note that some models from the [Converse
API](https://docs.aws.amazon.com/bedrock/latest/userguide/models-features.html)
might not support the AI Agent Node feature.
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.
The Conversation Analyzer uses the selected model to analyze session transcripts in [Cognigy Insights](https://docs-classic.cognigy.com/insights/overview.md). If no model is explicitly selected in **Manage > Settings > Generative AI Settings**, the Project's default LLM is used.
These models don't support token-sampling parameters such as `temperature`, `top_p`, and `top_k`. If you configure these parameters at the Node level or in **Custom Model Options**, they are automatically removed before the request is sent. To control model behavior, use the available thinking and budget settings instead.
The `gemini-2.5-flash-lite` and `gemini-3.5-flash-lite` models can return unstable results in the [LLM Prompt](https://docs-classic.cognigy.com/ai/agents/develop/node-reference/service/llm-prompt.md) Node. Test your Flows with these models before you use them in production.
This model defaults to `reasoning.effort: "low"` on the Responses API.
The `reasoning.effort` parameter controls how much effort the model uses to think through a request. Higher effort can help the model handle more complex requests, while lower effort can yield faster responses. Supported values, such as `"none"`, `"low"`, `"medium"`, and `"high"`, and their behavior may vary by model and API. Check your LLM provider's documentation for supported values and behavior.
To override this default, set `reasoning.effort` in **Custom Model Options**. The default `temperature` is `1.0`. To override this value, you must set `reasoning.effort: "none"` and adjust the **Temperature** parameter or set `temperature` in **Custom Model Options**.
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.