> ## Documentation Index > Fetch the complete documentation index at: https://docs.cognigy.com/llms.txt > Use this file to discover all available pages before exploring further. # Deprecations and Removals We are excited to announce a change in our software versioning system! This new system will make it easier for you to track releases by showing both their order and year, providing clearer insight into our updates and patches. Moving forward, we will use a new format: `YEAR.MINOR_RELEASE.PATCH_LEVEL`, where: * `YEAR` is the year of the release, for example, `2025`. * `MINOR_RELEASE` is the Nth minor release of the year, for example, the 10th minor release in 2025 is `10`. * `PATCH` is the Nth patch for a minor release, for example, the 1st patch for the 10th minor release is `1`. If no patches are released, the number is `0`. This page provides a list of removals and deprecations for native Cognigy features, as well as those that rely on third-party dependencies, such as LLMs (Large Language Models), Endpoints, and other external connectors. ## Terminology * **Deprecations**. A feature is considered as outdated and no longer recommended for use, with support limited to critical fixes only. The deprecation process starts with an announcement and continues until the feature is removed in future releases. * **Removals**. A feature is completely removed and no longer supported after the specified removal date. ## Cognigy Features The table lists Cognigy features that are deprecated and will be removed in future releases. | Feature | Deprecation Date | Removal date | Notes | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------- | -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | [Blind Mode Node](/ai/agents/develop/node-reference/analytics/blind-mode) | Cognigy 2026.18.0 | March 2027 | Use the [Data Redaction](/ai/platform-features/data-redaction) feature instead. | | Use of the **Model** field for deployment selection in [Microsoft Azure OpenAI](/ai/agents/develop/gen-ai-and-llms/providers/microsoft-azure-openai) Responses API requests | Cognigy 2026.18.0 | Cognigy 2027.3.0 | Use the **Deployment Name** field instead by activating the **Use deployment name as model** parameter. | | **Maximum Completion Tokens** and **Temperature** parameters in the [AI Agent](/ai/agents/develop/node-reference/ai/ai-agent) Node
**Sampling Method**, **Temperature**, **Top Percentage**, **Maximal Tokens**, **Frequency Penalty**, **Presence Penalty**, **Use Stops**, **Stops**, and **Seed** parameters in the [LLM Prompt](/ai/agents/develop/node-reference/service/llm-prompt) Node
**Temperature**, **Maximal Tokens**, **Presence Penalty**, **Frequency Penalty**, **Use Stops**, and **Stops** parameters in the [Search Extract Output](/ai/agents/develop/node-reference/other-nodes/search-extract-output) Node | Cognigy 2026.18.0 | April 2027 | For models that don't support these parameters, activate the **Ignore deprecated parameters** toggle. If you plan to use the deprecated parameters after their removal, migrate the configuration to the **Custom Options** field and activate the toggle. Otherwise, Custom Options might not override them for every provider and model combination. | | **Temperature** parameter in the [LLM Entity Extract](/ai/agents/develop/node-reference/other-nodes/llm-entity-extract) Node | Cognigy 2026.18.0 | April 2027 | For models that don't support this parameter, activate the **Ignore deprecated parameters** toggle. Configure model behavior via the **Custom Model Options** field and activate the toggle. Otherwise, Custom Options might not override it for every provider and model combination. | | **Temperature** parameter in the **LLM Entity Extraction Options** of the [Question](/ai/agents/develop/node-reference/basic/question) Node | Cognigy 2026.18.0 | April 2027 | For models that don't support this parameter, activate the **Ignore deprecated parameters** toggle. | | [Alexa NLU Connector](/ai/platform-features/nlu/external/nlu-connector-reference/alexa) and [Dialogflow NLU Connector](/ai/platform-features/nlu/external/nlu-connector-reference/dialog-flow) | Cognigy 2026.17.0 | January 2028 | You can still create and use these NLU Connectors until the removal date, but no further feature development is planned. Before the removal date, migrate to an alternative NLU provider, such as [Cognigy NLU](/ai/platform-features/nlu/external/nlu-connector-reference/cognigy-nlu). | | Legacy Extension runtime for trusted and untrusted Extensions | Cognigy 2026.16.0 | Cognigy 2026.21.0 | [Cognigy Serverless](/ai/for-developers/extensions#cognigy-serverless) is required starting with Cognigy 2026.21.0. | | [`GET /v2.0/profiles`](/api-reference/contact-profiles/get-contact-profiles) API method | Cognigy 2026.16.0 | Cognigy 2026.24.0 | Use the [`GET /v2.1/profiles`](/api-reference/contact-profiles/get-contact-profiles-performance) API method instead for improved performance when retrieving Contact Profiles. | | [`GET /v2.0/projects/{projectId}/logs`](/api-reference-logs/logs/get-log-entries) API method | Cognigy 2026.7.0 | Cognigy 2026.20.0 | Use the `GET /v2.1/projects/{projectId}/logs` API method instead. | | States tab in the **NLU** settings in the Flow editor, Set State and Reset State Nodes | Cognigy 2026.9.0 | Cognigy 2026.18.0 | This deprecation doesn't affect runtime behavior. After the removal, existing Flows containing these Nodes will remain fully supported and continue to run as expected. As an alternative, you can use [Intent Conditions](/ai/platform-features/nlu/intents/conditions) for controlling Intent recognition. | | States in the Interaction Panel, States functions, and States API methods | Cognigy 2026.7.0 | Cognigy 2026.12.0 | Delete your States and retrain your NLU model before the removal. Use [Intent Conditions](/ai/platform-features/nlu/intents/conditions) as an alternative for controlling Intent recognition. | | Support for the Completions API for custom LLMs | Cognigy 2026.6.0 | Cognigy 2026.24.0 | Refer to [your LLM provider's reference](/ai/agents/develop/gen-ai-and-llms/providers/all-providers) to switch to the appropriate Chat API before the removal date. | | [`DELETE /v2.0/conversations/{sessionId}`](/api-reference/conversations/deletes-a-conversation) API method | Cognigy 2026.5.0 | Cognigy 2026.20.0 | Use the `DELETE /v2.1/conversations/{sessionId}` API method instead. | | OAuth2 authentication in the [Send SMTP Email Node](/ai/agents/develop/node-reference/data/send-smtp-email) | Cognigy 2026.4.0 | Cognigy 2026.16.0 | Switch to the [OAuth2 Client Credentials](/ai/agents/develop/node-reference/data/send-smtp-email#oauth2-client-credentials-recommended) authentication method. | | Step Explorer and Message Explorer in Insights | Cognigy 2026.4.0 | Cognigy 2026.18.0 | - | | [Cognigy OData endpoint 2.3](/ai/agents/analyze/odata) | February, 2026 | To be determined | Switch to the Cognigy OData 2.4 endpoint. | | [Salesforce Service Cloud](/ai/escalate/handover-reference/salesforce) handover provider | February 14, 2026 | To be determined | Salesforce is retiring LiveAgent, Salesforce Chat, Embedded Chat, and Service Chat. Migrate to [Salesforce Messaging for In-App and Web](/ai/escalate/handover-reference/salesforce-miaw) before the removal date. For more information, read the [Salesforce release notes](https://help.salesforce.com/s/articleView?id=001790618\&type=1). | | [Genesys Cloud Guest Chat](/ai/escalate/handover-reference/genesys-cloud-guest-chat) handover provider | June 11, 2025 | To be determined | Due to [Genesys ACD Web Chat v2 deprecation](https://help.genesys.cloud/announcements/deprecation-removal-of-acd-web-chat-version-2/), migrate to [Genesys Cloud Open Messaging](/ai/escalate/handover-reference/genesys-cloud-open-messaging). | | [WebSocket and HTTP Webhook](/ai/escalate/handover-reference/genesys-cloud-open-messaging#prerequisites) for Genesys Cloud Open Messaging | April 29, 2025 | To be determined | Migrate to [Amazon EventBridge](/ai/escalate/handover-reference/genesys-cloud-open-messaging-with-amazon-eventbridge) | | Conversation counter API endpoint 2.0 | April 29, 2025 | To be determined | Use the [conversation counter API endpoint 3.0](/api-reference/analytics-30). | | [Cognigy OData 2.3](/ai/agents/analyze/odata#supported-versions) | December, 2025 | To be determined | Switch to the Cognigy OData 2.4 endpoint. | | `POST /v2.0/optionsresolver` API method for SaaS installations | - | Cognigy 2026.3.0 | If you use this method, update your setup before the release date to avoid disruptions. | | [Webchat v2](/webchat/v2/overview) | August 20, 2024 | February 2026 | Migrate to new [Webchat v3](/webchat/migration). | | LLM Prompt Node (legacy) | 2025.13.0 | Cognigy 2026.11.0 | Use the [LLM Prompt Node](/ai/agents/develop/node-reference/service/llm-prompt) instead. | | Handover Providers section in the Endpoint settings | March 18, 2025 | The end of January 2026 | Migrate to the new [Handover Providers](/ai/escalate/migration) interface. | | `say` verb with empty text content | - | April 29, 2025 | This removal affects the following Voice Gateway Nodes: [Say](/ai/agents/develop/node-reference/basic/say), [Question](/ai/agents/develop/node-reference/basic/question), and [Optional Question](/ai/agents/develop/node-reference/basic/optional-question). | | [actions.think, api.think](/ai/for-developers/code/api-functions) | April 1, 2025 | June 2025 | Use `api.thinkV2()` and `actions.thinkV2()` instead. | | Insights Beta API | April 1, 2025 | June 10, 2025 | Use the [Cognigy OData endpoint](/ai/agents/analyze/odata). | | Intent Sentence Generation, Lexicon Generation, Flow Generation, Adaptive Card Generation in Project settings | April 15, 2025 | June 24, 2025 | Select the LLM for all these features from the [Design-Time Generative LLM Features list](/ai/agents/develop/gen-ai-and-llms/generative-ai#design-time-generative-ai-features). | | [AudioCodes Nodes](/ai/agents/develop/node-reference/voice/audiocodes/overview) and [Generic Voice Nodes](/ai/agents/develop/node-reference/voice/generic/overview) | March 4, 2025 | Q3 2026 | After the end of February 2025, you won't be able to create new Nodes, but you can still edit or clone existing ones. Flows with these Nodes will continue to work after the deprecation date. Consider the [Cognigy Voice Gateway](/voice-gateway/overview) product and its [Voice Gateway Nodes](/ai/agents/develop/node-reference/voice/voice-gateway/overview) as an alternative to AudioCodes. | | [AudioCodes Endpoint](/ai/agents/deploy/endpoint-reference/audiocodes) and [AudioCodes channel](/ai/agents/develop/nodes/channels) | April 2025 | Q2 2026 | Migrate to the [Cognigy Voice Gateway](/voice-gateway/overview) product and use its [Voice Gateway Endpoint](/ai/agents/deploy/endpoint-reference/voice-gateway) as an alternative to AudioCodes. | | [Amazon Alexa](/ai/agents/deploy/endpoint-reference/amazon-alexa) and [Dialogflow](/ai/agents/deploy/endpoint-reference/dialogflow) Endpoints | Cognigy 2026.17.0 | January 2028 | | | Understood Messages in the [Intent Trainer](/ai/platform-features/nlu/intents/intent-trainer) and Insights reports ([Overview](/insights/reports/overview) and [NLU Performance](/insights/reports/nlu-performance)) | December 2024 | From Insights reports: Cognigy 2025.19 | Use the Goals and Tasks concept in order to measure whether your AI Agent understood a particular phrase. The Understood Messages concept relies on specific rules that don't work for all customers. | | `understood` field in the [Cognigy OData endpoint](/ai/agents/analyze/odata) | December 2024 | Cognigy 2026.1.0 | Use the [Goals collection](/ai/agents/analyze/odata#goals) in the Cognigy OData endpoint. | | Support for the `request-promise` library in [transformers](/ai/for-developers/transformers/overview) | Cognigy 2025.25.0 | - | Review your transformer code to ensure it is compatible with the [Axios library](https://axios-http.com/docs/req_config). | | Any Slots | - | September 3, 2024 | Use the [LLM Entity Extraction Node](/ai/agents/develop/node-reference/other-nodes/llm-entity-extract) to identify Slots in the user input via LLMs. | | GPT Conversation | - | September 17, 2024 | If you are still using these Nodes, they will continue to work in the existing Flows created before [Cognigy 4.85](/release-notes/4.85). | ## Third-Party Products ### LLMs The table lists LLMs that are deprecated and will be removed. Once the LLM provider removes the model, it will stop working in Cognigy. This change could cause disruptions to your AI Agent if the model is still being used in the Flow. If you've added models from the list as custom models in Cognigy, switch to [newer models](/ai/agents/develop/gen-ai-and-llms/model-support-by-feature) before the shutdown date. | Models | Deprecation Date | Removal Date | Notes | | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------- | --------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **OpenAI** | | | | | `gpt-5-chat-latest` | April 22, 2026 | July 23, 2026 | Migrate to `gpt-5.6-sol`. For more information, read the [OpenAI documentation](https://platform.openai.com/docs/deprecations). | | `gpt-4.1-nano` | - | October 23, 2026 | For more information, read the [OpenAI documentation](https://platform.openai.com/docs/deprecations). | | `gpt-3.5-turbo-0301`, `gpt-3.5-turbo-0613`, `gpt-3.5-turbo-16k-0613` | January 10, 2024 | September 13, 2024 | For more information, read the OpenAI documentation: [gpt-3.5-turbo-0613 and gpt-3.5-turbo-16k-0613](https://platform.openai.com/docs/deprecations#2023-06-13-updated-chat-models) and [gpt-3.5-turbo-0301](https://platform.openai.com/docs/deprecations#2024-06-06-gpt-4-32k-and-vision-preview-models). | | `gpt-4-vision-preview`, `gpt-4-1106-vision-preview` | June 17, 2024 | December 6, 2024 | For more information, read the [OpenAI documentation](https://platform.openai.com/docs/deprecations). | | **Google GenAI** | | | | | `gemini-embedding-001` | - | July 14, 2026 | Migrate to `gemini-embedding-2`. For more information, read the [Google Vertex AI documentation](https://ai.google.dev/gemini-api/docs/deprecations). | | **Google Gemini** | | | | | `gemini-2.5-pro` | - | October 16, 2026 | The model remains functional until Google's shutdown date. Migrate to `gemini-3.5-flash` or another supported model. For more information, read the [Google Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable). | | `gemini-2.5-flash` | - | October 16, 2026 | For more information, read the [Google Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable). | | `gemini-embedding-001` | - | July 14, 2026 | For more information, read the [Google Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable). | | `gemini-2.5-flash-lite` | - | Not before October 16, 2026 | For more information, read the [Google Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable). Google recommends migrating to `gemini-2.5-flash`. | | `gemini-2.0-flash` and `gemini-2.0-flash-lite` | - | June 1, 2026 | For more information, read the [Google Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable). | | `gemini-1.5-flash` | - | September 24, 2025 | For more information, read the [Google Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable). | | `gemini-1.5-pro` | - | September 24, 2025 | For more information, read the [Google Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable). | | `gemini-1.0-pro` | February 15, 2024 | April 21, 2025 | For more information, read the [Google Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable). Google recommends migrating to Gemini 2.0 Flash. | | `gemini-3.1-flash-lite-preview` | March 3, 2026 | May 25, 2026 | For more information, read the [Google Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable). Google recommends migrating to Gemini 3.1 Flash Lite. | | **Google Vertex AI** | - | | | | `chat-bison@002`, `chat-bison-32k@002`, `code-bison@002`, `code-bison-32k@002`, `codechat-bison@002`, `codechat-bison-32k@002`, `text-bison@002`, `text-bison-32k@002` | - | October 9, 2024 | For more information, read the [Google Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/legacy/legacy-models). Google recommends migrating to Gemini 2.0 Flash by using the following [guide](https://cloud.google.com/vertex-ai/generative-ai/docs/migrate/migrate-palm-to-gemini). | | `text-bison-001` | May 2023 | April 21, 2025 | Google recommends migrating to Gemini 2.0 Flash Lite. For more information, read the [Google Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions#legacy-stable). | | **Anthropic** | | | | | `claude-3-haiku` | February 19, 2026 | Cognigy 2026.10.0 | Migrate to `claude-haiku-4-5`. For more information, read the [Anthropic](https://docs.anthropic.com/en/docs/about-claude/model-deprecations#model-status) documentation. | | `claude-sonnet-3-7` | October 28, 2025 | Cognigy 2026.5.0 | For more information, read the [Anthropic](https://docs.anthropic.com/en/docs/about-claude/model-deprecations#model-status) documentation. | | `claude-3-opus` | June 30, 2025 | January 2026 | For more information, read the [Anthropic](https://docs.anthropic.com/en/docs/about-claude/model-deprecations#model-status) documentation. | | `claude-3-sonnet` | January 21, 2025 | July 21, 2025 | For more information, read the [Anthropic](https://docs.anthropic.com/en/docs/about-claude/model-deprecations#model-status) documentation. | | `claude-1.0`, `claude-1.1`, `claude-1.2`, `claude-1.3`, `claude-1.3-100k`, `claude-instant-1.0`, `claude-instant-1.1`, `claude-instant-1.1-100k`, `claude-instant-1.2` | September 4, 2024 | November 6, 2024 | For more information, read the [Anthropic](https://docs.anthropic.com/en/docs/resources/model-deprecations#2024-09-04-claude-1-and-instant-models) documentation. Anthropic recommends migrating to `claude-3-haiku-20240307`. | | **Microsoft Azure OpenAI** | | | | | `gpt-5-chat-latest` (Cognigy alias for `gpt-5-chat` versions 2025-08-07 and 2025-10-03) | - | May 13 and June 29, 2026 | Migrate to `gpt-chat-latest`. For more information, see the [Azure OpenAI documentation](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models). | | `gpt-5-nano`, `gpt-5-mini` | - | February 9, 2027 | Migrate to a more recent model before the removal date. For more information, see the [Azure OpenAI documentation](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule). | | `gpt-4o` (version 2024-05-13) | - | October 1, 2026 | Migrate to `gpt-5.1` before the removal date. For more information, see the [Azure OpenAI documentation](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule). | | `gpt-4.1-nano` | - | October 14, 2026 | Migrate to a more recent model before the removal date. For more information, see the [Azure OpenAI documentation](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule). | | `gpt-4o` (versions 2024-08-06 and 2024-11-20), `gpt-4o-mini`, `gpt-4.1`, `gpt-4.1-mini` | - | April 14, 2027 | Migrate to `gpt-5.1` for `gpt-4o` and `gpt-5-mini` for `gpt-4o-mini`. For the `gpt-4.1` models, migrate to a more recent model. For more information, read the [Azure OpenAI documentation](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule). | | `gpt-35-turbo` (version 1106) | - | No earlier than November 17, 2024 | For more information, read the [Azure OpenAI documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/model-retirements#current-models). | | `gpt-35-turbo-16k` (version 0613), `gpt-35-turbo` (versions 0613, 0301) | - | January 27, 2025 | For more information, read the [Azure OpenAI documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/model-retirements#current-models). | | `gpt-35-turbo` (version 0125) | - | No earlier than February 22, 2025 | For more information, read the [Azure OpenAI documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/model-retirements#current-models). | | **Mistral AI** | | | | | `pixtral-large-latest` | - | May 31, 2026 | Mistral removed this model from their API. Migrate to another Mistral model such as `mistral-large-latest`. Requests to this model return a "model retired" error. For more information, read the [Mistral AI documentation](https://docs.mistral.ai/models/overview). | | `pixtral-12b-2409` | - | December 31, 2025 | For more information, read the [Mistral AI documentation](https://docs.mistral.ai/). | | `mistral-medium-latest` | - | August 31, 2026 | For more information, read the [Mistral AI documentation](https://docs.mistral.ai/). | | **Amazon Bedrock** | | | | | `amazon.nova-premier-v1:0` | - | September 14, 2026 | For more information, read the [Amazon Bedrock documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle.html). | | `anthropic.claude-3-5-sonnet-20240620-v1:0` | March 1, 2026 | Cognigy 2026.10.0 | For more information, read the [Amazon Bedrock documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle.html). | | **Aleph Alpha** | | | | | `luminous` | Cognigy 2026.10.0 | Cognigy 2026.24.0 | Select other [models to support your use case](/ai/agents/develop/gen-ai-and-llms/model-support-by-feature). | | `luminous-embedding-128` | Cognigy 2026.10.0 | Cognigy 2026.11.0 | Select other [models to support your use case](/ai/agents/develop/gen-ai-and-llms/model-support-by-feature). | ## More Information * [All Releases](/release-notes/index)