# Deploy an LLM from the playground

> Deploy an LLM from the playground - LLM blueprints and all their associated settings are registered
> in Registry and can be deployed and monitored with the Console.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-05-06T18:17:09.559107+00:00` (UTC).

## Primary page

- [Deploy an LLM from the playground](https://docs.datarobot.com/en/docs/agentic-ai/playground-tools/deploy-llm.html): Full documentation for this topic (HTML).

## Related documentation

- [Agentic AI](https://docs.datarobot.com/en/docs/agentic-ai/index.html): Linked from this page.
- [RAG workflows](https://docs.datarobot.com/en/docs/agentic-ai/playground-tools/index.html): Linked from this page.
- [playground](https://docs.datarobot.com/en/docs/agentic-ai/playground-tools/playground-overview.html): Linked from this page.
- [Use Case](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/usecases/index.html): Linked from this page.
- [create an LLM blueprint](https://docs.datarobot.com/en/docs/agentic-ai/playground-tools/build-llm-blueprints.html): Linked from this page.
- [Registry's workshop](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/index.html): Linked from this page.
- [Bolt-on Governance API](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/structured-custom-models.html#chat): Linked from this page.
- [compare LLMs](https://docs.datarobot.com/en/docs/agentic-ai/playground-tools/compare-llm.html): Linked from this page.
- [Preview feature](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-create-custom-model.html#select-a-resource-bundle): Linked from this page.
- [custom environment](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/custom-models/custom-model-environments/custom-environments.html): Linked from this page.
- [DRUM](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/custom-model-drum.html): Linked from this page.
- [generated compliance documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-compliance-doc.html): Linked from this page.
- [make requests to the DataRobot LLM gateway](https://docs.datarobot.com/en/docs/agentic-ai/genai-code/dr-llm-gateway.html): Linked from this page.
- [Credentials Managementpage of the DataRobot platform](https://docs.datarobot.com/en/docs/platform/acct-settings/stored-creds.html#credentials-management): Linked from this page.
- [Microsoft-hosted LLMs](https://docs.datarobot.com/en/docs/reference/gen-ai-ref/llm-availability.html): Linked from this page.
- [test the model](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-test-custom-model.html): Linked from this page.
- [create new versions](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-custom-model-versions.html): Linked from this page.
- [provide the registered model or version details](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-register-cus-models.html#register-a-model-from-the-workshop): Linked from this page.
- [configure the deployment settings](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-deploy-models.html#configure-deployment-settings): Linked from this page.
- [Monitoring support for generative models](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-monitoring/nxt-genai-monitoring.html#monitor-a-deployed-generative-model): Linked from this page.
- [playground deployment considerations](https://docs.datarobot.com/en/docs/reference/gen-ai-ref/genai-consider.html#playground-deployment-considerations): Linked from this page.

## Documentation content

Use an LLM [playground](https://docs.datarobot.com/en/docs/agentic-ai/playground-tools/playground-overview.html) in a [Use Case](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/usecases/index.html) to [create an LLM blueprint](https://docs.datarobot.com/en/docs/agentic-ai/playground-tools/build-llm-blueprints.html). Set the blueprint configuration, specifying the base LLM and, optionally, a system prompt and vector database. After testing and tuning the responses, the blueprint is ready for registration and deployment.

You can create a text generation custom model by sending the LLM blueprint to [Registry's workshop](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/index.html). The generated custom model automatically implements the [Bolt-on Governance API](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/structured-custom-models.html#chat), which is particularly useful for building conversational applications.

Follow the steps below to add the LLM blueprint to the workshop:

1. In a Use Case, from thePlaygroundstab, click the playground containing the LLM you want to register as a blueprint.
2. In the playground,compare LLMsto determine which LLM blueprint to send to the workshop, then do either of the following:
3. In theSend to the workshopmodal, do the following, then clickSend to the workshop:
4. ClickSend to the workshop. In the lower-right corner of the LLM playground, notifications appear as the LLM is queued and registered. When notification of the registration's completion appears, clickGo to the workshop: The LLM blueprint opens in the Registry's workshop as a custom model with theText Generationtarget type:
5. On theAssembletab, in theRuntime Parameterssection, configure the key-value pairs required by the LLM, including the LLM service's credentials and other details. To add these values, click the edit iconnext to the available runtime parameters. Premium: DataRobot LLM gatewayIf your organization has access to the DataRobot LLM gateway, you don't need to configure any credentials. Confirm that theENABLE_LLM_GATEWAY_INFERENCEruntime parameter is present and set toTrue. If necessary, configure thePROMPT_COLUMN_NAME(the default column name ispromptText), and then skip to the next step. You can alsomake requests to the DataRobot LLM gateway. To configureCredentialtypeRuntime Parameters, first, add the credentials required for the LLM you're deploying to theCredentials Managementpage of the DataRobot platform: Microsoft-hosted LLMsAmazon-hosted LLMsGoogle-hosted LLMsForMicrosoft-hosted LLMs, use the following:Credential type: API Token (notAzure)Runtime Parameters:KeyDescriptionOPENAI_API_KEYSelect theAPI Tokencredential, created on theCredentials Managementpage, for the Azure OpenAI LLM API endpoint.OPENAI_API_BASEEnter the URL for the Azure OpenAI LLM API endpoint.OPENAI_API_DEPLOYMENT_IDEnter the name of the Azure OpenAI deployment of the LLM, chosen when deploying the LLM to your Azure environment. For more information, see the Azure OpenAI documentation on how toDeploy a model. The default deployment name suggested by DataRobot matches the ID of the LLM in Azure OpenAI (for example, gpt-35-turbo). Modify this parameter if your Azure OpenAI deployment is named differently.OPENAI_API_VERSIONEnter the Azure OpenAI API version to use for this operation, following the YYYY-MM-DD or YYYY-MM-DD-preview format (for example, 2023-05-15). For more information on the supported versions, see theAzure OpenAI API reference documentation.PROMPT_COLUMN_NAMEEnter the prompt column name from the input .csv file. The default column name is promptText.ForAmazon-hosted LLMs, use the following:Credential type: AWSRuntime Parameters:KeyDescriptionAWS_ACCOUNTSelect anAWScredential, created on theCredentials Managementpage, for the AWS account.AWS_REGIONEnter the AWS region of the AWS account. The default is us-west-1.PROMPT_COLUMN_NAMEEnter the prompt column name from the input .csv file. The default column name is promptText.ForGoogle-hosted LLMs, use the following:Credential type: Google Cloud Service AccountRuntime Parametersare:KeyDescriptionGOOGLE_SERVICE_ACCOUNTSelect aGoogle Cloud Service Accountcredential created on theCredentials Managementpage.GOOGLE_REGIONEnter the GCP region of the Google service account. The default is us-west-1.PROMPT_COLUMN_NAMEEnter the prompt column name from the input .csv file. The default column name is promptText.
6. In theSettingssection, ensureNetwork accessis set toPublic.
7. After you complete the custom model assembly configuration, you cantest the modelorcreate new versions. DataRobot recommends testing custom LLMs before deployment.
8. Next, clickRegister a model,provide the registered model or version details, then clickRegister modelagain to add the custom LLM to Registry. The registered model version opens on theRegistry > Modelstab.
9. From theModelstab, in the upper-right corner of the registered model version panel, clickDeployandconfigure the deployment settings. For more information on the deployment functionality available for generative models, seeMonitoring support for generative models.

For more information on this process, see the [playground deployment considerations](https://docs.datarobot.com/en/docs/reference/gen-ai-ref/genai-consider.html#playground-deployment-considerations).