---
sourceDocument: Zurich Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/intelligent-experiences

 Release :

    - zurich

ft:locale :

    - en-US

ft:publication_title :

    - Zurich Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Model provider updates

# Model provider updates {#ariaid-title1}

Release version: Zurich  
Updated September 22, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 8 minutes to read
Summarize  
![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI  
This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.  

## Summary of Model provider updates

This document provides detailed updates about the availability, enhancements, and lifecycle changes for large language models (LLMs) and related AI models within the ServiceNow platform.
It covers ServiceNow Otto skills, agents, agentic workflows, and AI-powered features both inside and outside ServiceNow Otto, highlighting model cards that describe model context, intended use, training data, and limitations.
The updates span releases from November 2024 through October 2026 and include new model introductions, retirements, deprecations, and changes in default providers and configurations.
Show full answer Show less  

## Key Features

* **Model Cards:** Provide essential information about each AI model, including ServiceNow's own models (such as Gemma and ServiceNow large/small language models) and third-party models (Google Gemini, AWS Claude, Azure OpenAI). These cards help customers understand appropriate use cases, limitations, and training context.
* **New Models and Releases:**
  * Gemma 4 26B-A4B introduced as a selectable enterprise AI model for both large and small language use cases.
  * Google Gemini 3.5 Flash replaces retired Gemini 2.5 models starting October 2026.
  * Claude Sonnet 4.6 replaces retired Claude Sonnet 4.5 in October 2026.
  * Advanced 12B general-purpose small language models released in 2025 with enhanced instruction adherence, multilingual support, and expanded capabilities for text-to-code, text-to-flow, and content moderation.
* **Model Provider Flexibility:** ServiceNow has shifted from a single default model provider (Now LLM Service) to integrated third-party providers (Google Gemini, AWS Claude, Azure OpenAI), allowing customers to select models best suited to their needs via the AI Admin Hub console.
* **Restricted Models:** Certain models are designated as restricted, supporting specific platform features but not selectable for custom skills or agents.
* **Configuration Guidance:** Customers must update prompt and generative AI configuration records to specify exact model names instead of generic references, especially following model retirements and deprecations.
* **Speech AI and Content Moderation Models:** Voice AI models support speech-to-text and text-to-speech, while the AI Guardian model handles content moderation and prompt injection detection.
* **CSAT Prediction Model:** A specialized model ingests conversations to predict customer satisfaction scores and explanatory factors.
* **Improvements in Output Format and Instruction Following:** Now LLM Service enhancements include JSON output support for easier application integration, deterministic and lower token consumption responses, and improved instruction adherence for more accurate and actionable outputs.

## Key Outcomes for ServiceNow Customers

* **Model Selection and Updates:** Customers should review their AI skills, agents, and generative AI configurations to replace retired models (e.g., Gemini 2.5, Claude Sonnet 4.5) with supported versions like Gemini 3.5 Flash and Claude Sonnet 4.6.
* **Transition Planning:** The ServiceNow large and small language models (V2) are deprecated for new development and planned for retirement by December 2026, with Gemma models as replacements.
* **Default Model Provider Changes:** Default models for base system skills and agents have shifted to integrated third-party providers, but customers retain the option to select Now LLM Service models for a ServiceNow-hosted AI experience.
* **Configuration Best Practices:** Explicitly name models in configurations to avoid disruptions from generic references and model retirements. Verify reasoningeffort settings for GPT-5 Mini to ensure desired behavior.
* **Enhanced Multilingual and Functional Support:** Newer models provide better support for multiple languages, including Japanese, and improved capabilities for text generation, summarization, code generation, and safety moderation, enabling more effective automation and AI-driven workflows.
* **Improved Integration and Efficiency:** JSON output and deterministic responses reduce errors and token consumption, helping customers build more reliable and cost-efficient AI integrations.  
Review
these updates to learn which model providers and models are available for your skills and agents. Review the model cards for information about how each model is intended to be used.

## Model cards

Large language models (LLMs) are complex machine-learning models that are trained on large datasets like websites and documentation to perform language-related tasks. Examples include text generation for case summaries and
resolution notes.

Model cards explain the specific model's context, intended use, training data, limitations, and other important information.

These model cards reflect the AI models that power various features within the ServiceNow platform. These include skills, agents, and agentic workflows within ServiceNow Otto as well as AI powered features outside of ServiceNow Otto. To see which model a ServiceNow Otto skill, agent, or agentic workflow is using, you can check the skill list in the AI Admin Hub console and review the LLM service column.

Model
card for Gemma 4 26B A4B
:   Selectable ServiceNow Otto model for enterprise AI that enhances text-based automation and content generation in ServiceNow workflows, including requester OOTB skills, custom skills, and agentic use cases.

[Model card for ServiceNow large language model (V2)](https://downloads.docs.servicenow.com/resource/enus/infocard/sn-llm-v2.pdf)

:   ServiceNow Otto model for enterprise AI that enhances text-based automation and content generation in ServiceNow workflows, including requester OOTB skills, custom skills, and agentic use cases.

    This model is available for Generative AI Controller application 15.1.0 or higher.

[Model card for ServiceNow small language model (V2)](https://downloads.docs.servicenow.com/resource/enus/infocard/sn-slm-v2.pdf)

:   ServiceNow Otto model for enterprise AI that enhances text-based automation and content generation in ServiceNow workflows, including creator and fulfiller OOTB skills as well as custom skills.

    This
    model is available for Generative AI Controller application 11.2 or higher.

[Model card for ServiceNow third party large language model](https://downloads.docs.servicenow.com/resource/enus/infocard/third-party-llm.pdf)
:   ServiceNow Otto models used for AI-driven solutions for text generation, summarization, and conversational AI.

[Model card for ServiceNow Voice AI Speech-to-Text and Text-to-Speech models](https://downloads.docs.servicenow.com/resource/enus/infocard/sn-voice.pdf)
:   Models used within ServiceNow AI Voice Agents for converting spoken user input to text and generating natural-sounding speech from AI responses.

[Model card for ServiceNow
AI Guardian model](https://downloads.docs.servicenow.com/resource/enus/infocard/sn-na-guardian.pdf)
:   This model provides content moderation and helps identify different kinds of prompt injection attacks and offensive content.

[Model card for ServiceNow Inferred CSAT and Factors large language model](https://downloads.docs.servicenow.com/resource/enus/infocard/csat-llm.pdf)
:   This model is designed to ingest a conversation and predict a CSAT score as well as factors that explain the predicted score.

## October 2026 {#now-llm-model-updates__section_october_2026}

The October release adds models to the Now LLM Service and to Google Gemini. It also retires the Gemini 2.5 models and Claude Sonnet 4.5, and begins the deprecation of the Now LLM Service V2 models.  
* New model in the Now LLM Service: Gemma 4 26B-A4B is available for both large and small language model use cases. Third-party models remain the default. You can select the Now LLM Service for your skills and agents instead of the default.

* New restricted model: Gemini 3.7 Flash supports the Build Agent. You can't select it for your skills and agents.

* Gemini
  2.5 models retired: Gemini 2.5 Pro, Gemini 2.5 Flash, and Gemini 2.5 Flash Lite are retired on October 8, 2026. Gemini 3.5 Flash replaces all three models. Review your skills, agents, and generative AI configurations for
  references to the retired models, and select Gemini 3.5 Flash instead.

* Claude
  Sonnet 4.5 retired: Claude Sonnet 4.5 is retired on October 8, 2026. Claude Sonnet 4.6 replaces it. Select Claude Sonnet 4.6 for your skills and agents.

* V2 models deprecated for new development: The ServiceNow large language model (V2) and small language model (V2) are deprecated for new development. Your existing skills and agents continue to work. Retirement is planned for the December release,
  when these models are replaced by Gemma.

{#now-llm-model-updates__ul_october_2026}

## September 2026 {#now-llm-model-updates__section_september_2026}

The September release adds restricted models from AWS Anthropic. Restricted models support specific features only. You can't select them for your skills and agents.

This release doesn't add any general purpose models. The models that you can select in the AI Admin Hub console are unchanged.  
* Claude Sonnet 5 and Claude Fable 5 support the Build Agent.

* Restricted replaces limited: The card now uses Restricted instead of Limited to identify models that you can't configure. Claude Opus 4.6 and Gemini 2.5 Flash Lite use the new
  term. Their supported features haven't changed. Gemini 2.5 Flash Lite is retired on October 8, 2026, and is replaced by Gemini 3.5 Flash.

{#now-llm-model-updates__ul_september_2026}

## July 2026 {#now-llm-model-updates__section_july_2026}

The Now LLM Service model strategy has moved toward integrated model provider flexibility. Store application updates have started shipping, and the default model for base system skills and agents is changing from the Now LLM Service to an integrated third-party model provider. If you haven't changed the default model for a skill, that skill uptakes the new default.  
* Integrated third-party model providers: The integrated third-party model providers are Google Gemini, AWS Claude, and Azure OpenAI.

* New general purpose models: You can select these models for your skills and agents in the AI Admin Hub console. Model availability varies by your instance, your configuration, and your geographic region.

  * Azure OpenAI: GPT-5.1, GPT-5.4 Mini, and GPT-5.1 Mini
  * Google Gemini: Gemini 3.5 Flash
* GPT-5.2 deprecated: GPT-5.2 is no longer available as a model option. GPT-5.4 replaces it. If you selected GPT-5.2, update your model configuration records to select GPT-5.4. References to GPT-5.2 aren't redirected
  automatically.

* The Now LLM Service is still supported: The change to the default model provider doesn't remove access to the Now LLM Service. You can still select it for your skills and agents if you require a ServiceNow hosted model.

* Existing selections preserved: If you have already selected a model provider, that configuration is preserved. The update doesn't overwrite an explicit selection.

* Changing your model provider: To select a model provider other than the default, review the providers that are allowed for your instance in AI Control Tower. Navigate to ConfigurationsControlsAI model providers, and then make your changes in the ServiceNow Otto
  Admin Center by navigating to SettingsManage AI ModelsManage Model Providers.

* Explicit
  model names required: Update prompt and generative AI configuration records that use generic large or small model references. Reference a specific supported model by name instead.

{#now-llm-model-updates__ul_july_2026}

## June 2026 {#now-llm-model-updates__section_june_2026}

The June release includes updates to third-party model defaults. It also contains a change to the default reasoning effort setting for GPT-5 Mini, and the retirement of the Now LLM long-term support (LTS) SKU.  
* Third-party default model version update: Teams that did not update their third-party default model versions to the latest available versions in the May release must do so in the June release. GAIC 13.1.2 is the required
  version for this update.

* GPT-5 Mini: `reasoning_effort` default change: The default `reasoning_effort` setting for GPT-5 Mini has changed from `none` to `minimal`. This change is included in
  GAIC Snapshot 14.0.0, which is compatible with Now Assist for Platform 12.0.0.

  Teams using GPT-5 Mini should run regression and functional testing to confirm that the new default works as expected. If you explicitly set `reasoning_effort` in your generative AI config additional
  properties, smoke test to verify there are no unexpected effects. If you have `reasoning_effort: none` set in additional properties, update the value to `minimal` and run regression and functional
  testing.
* Claude Sonnet 4.0 retirement: Claude Sonnet 4.0 references are being redirected on the backend. No team action is required.

  * `claude_large` / Claude 4.0 Sonnet redirects to Claude 4.5 Sonnet
  * `claude_small` / Claude 4.0 Sonnet redirects to Claude 4.5 Sonnet
* Now LLM LTS SKU retired: ServiceNow no longer offers the LTS model SKU. There are no testing requirements or expectations for teams related to this retirement.

## May 2025 {#now-llm-model-updates__section_qmv_nns_jfc}

An advanced 12B general-purpose small language model (SLM) with a singular, high-performance architecture that supports a wide range of tasks in ServiceNow's context was released. Fine-tuned on Mistral-Nemo-12B-Instruct, this model
is designed and optimized for tasks like Agent Assist, Text-to-Flow, Text-to-Cypher, Safety \& Content Moderation and Text-to-Code.  
Key Enhancements:

* Enhanced instruction adherence: Improved the model's capability to accurately interpret and follow user instructions, ensuring that the model can better understand and execute complex commands. Leading to more precise and reliable outcomes than previous releases.
* Increased context window: Increased context window from 16K to 32K, enabling the model to better understand long-form inputs. This increase maintains coherence over extended interactions, and supports more complex tasks with richer contextual awareness.
* Improved multilingual proficiency: Boosted performance across languages compared to previous releases, with notable enhancements in Japanese processing.
* Optimized for ServiceNow workflow related capabilities: Extended support coverage for Text-to-Flow, and improved the performance of Text-to-Code, Text-to-Cypher etc.
* Continuously enhanced model deployment consolidation: Integrates ServiceNow-related tasks into a single model, reducing system complexity at the same time while elevating overall performance.
{#now-llm-model-updates__ul_y25_sns_jfc}

## March 2025 {#now-llm-model-updates__section_yks_3cn_m2c}

A powerful 12B general-purpose small language model (SLM) designed to enhance a wide range of applications, including text-to-code and agent use cases was released. Fine-tuned on Mistral-Nemo-12B, it streamlines deployment and
consolidates multiple functionalities into a singular, architecture.  
Key Enhancements:

* Optimized to fulfill use cases: Enhances case summarization, chat summarization, resolution notes, and knowledge base generation across supported languages, including improvements in Japanese quality.
* Superior text-to-code and text-to-cypher performance: Delivers major advancements in Glide JavaScript and generic JavaScript editing and generation, along with improved accuracy in query generation and execution for structured databases.
* Robust content moderation and safety: Provides stronger protection against adversarial prompts, jail-breaking attempts, and harmful content generation, ensuring safer deployment with built-in content filtering.
* Unified model deployment:integrates ServiceNow-related tasks into a single model, thereby reducing system complexity while elevating overall performance.
* Improved instruction adherence: Delivers better instruction following and consistency across varying levels of prompt and instruction strictness than the current text-to-text NowLLM.
{#now-llm-model-updates__ul_xv4_1q5_m2c}

## November 2024 {#now-llm-model-updates__section_o24_ym3_gdc}

Several key improvements were added to the Now LLM Service that are aimed at enhancing performance and quality.  
* Multilingual support: Now LLM Service supports 8 additional languages, enabling global teams to use the model in their native languages.

  The supported languages are: English, German, French, Japanese, Dutch, French Canadian, Spanish, Brazilian Portuguese, and Italian.
* JSON format support: The model now provides output in JSON format, making it easier for developers to integrate with various applications and automate workflows seamlessly.
  * Deterministic responses: JSON mode ensures structured, consistent output, which improves predictability and reliability when integrating with applications.
  * Error reduction: Unlike free-form text mode, JSON responses are less prone to format errors or stray characters, minimizing integration issues.
  * Lower token consumption: The fixed structure of JSON can reduce token usage, making it more efficient and cost-effective for applications with high response frequency.
  {#now-llm-model-updates__ul_kmm_b43_gdc}
* Improvements in instruction following: The model has been fine-tuned to understand and follow instructions more precisely. This enables the model to deliver more to-the-point and actionable responses, helping users get the information they need faster and more efficiently.
{#now-llm-model-updates__ul_mwj_nn3_gdc}

*[\>]: and then