This article covers how to translate using an xAI Grok model by creating an LLM Profile, which controls the model used, the translation prompt, and other translation settings. You can then use the LLM Profile to translate in Smartling by assigning it to the translation step of a workflow, or by using it with one of Smartling's instant machine translation integrations.
xAI's Grok models can be used as a translation provider in Smartling, as part of a translation workflow or with any of Smartling's instant machine translation integrations.
Prerequisites
Before you begin, ensure you have the following:
- An xAI account with API access enabled. Grok (xAI) is BYOK only. Smartling-provisioned credentials are not available for this provider.
- An xAI API key, generated from the xAI Console
Please review xAI’s data policies before you begin translating, as xAI’s data handling terms are different from other Smartling-supported LLM providers. This is not legal advice. Please review xAI’s terms directly and consult your legal team if your organization has data governance requirements.
Supported models & languages
Smartling supports text/chat models available through the xAI API. In the LLM Profile, you enter the model name directly into the xAI model field (e.g., grok-4.5). For model information, see xAI's Models documentation.
xAI does not publish an official supported-language list for Grok models. As with other LLM providers, translation quality will generally be strongest for high-resource languages and may vary for less common or low-resource languages.
Token and rate limits
LLM models use tokenizers to break text into units called tokens, and token usage includes both input and output tokens. xAI enforces its own rate limits per model and account tier.
Info: If a token or rate limit is exceeded, an error will appear in Smartling on the Profiles page in the AI Hub. If the overall or monthly token limit has been reached, the LLM Profile may stop generating translations.
Setting up Grok (xAI) as a translation provider
Step 1: Create an API key in xAI
- Sign in to the xAI Console.
- Create a new API key and copy it somewhere safe.
Step 2: Add your credentials in Smartling
- From the top navigation of your dashboard, access the AI Hub.
- Navigate to the Credentials section.
- Click Add Provider Credential.
- Enter the following information:
- MT or LLM Provider (required): From the dropdown, select Grok (xAI).
- Credential Name (required): A nickname to help you identify this credential later.
- Credential Description (optional)
- xAI access token (required): Paste the API key you generated in the xAI Console.
- Click Save to store the credential.
For more information on provider credentials, see MT and LLM Provider Credentials (BYOK).
Step 3: Create an LLM Profile using your Grok (xAI) credentials
Once your credential is saved, use it to create an LLM Profile. Follow the general steps in How to create an LLM Profile, selecting Grok (xAI) as your provider.
Grok (xAI)-specific fields on the Configuration Details step:
- Provider Credentials: Select the credential you created in Step 2 from the dropdown.
- xAI model (required): Enter the model name directly, e.g., grok-4.5.
- Linguistic Packages: Select which of your existing Linguistic Packages Smartling should use for prompt tooling with RAG. Linguistic Packages selected here only apply when the LLM Profile is used for one of Smartling's instant MT integrations or the MT API. When the LLM Profile is used in a translation workflow or for translation suggestions in the CAT Tool, the project's own Linguistic Package is used automatically instead.
- Parameter Details (optional): Grok (xAI) profiles have two tunable parameters, Temperature and Top P (both 0–1, default is the model's own default), plus a Disable hallucination detection checkbox that turns off Smartling's hallucination detection for this profile. For more information, see Translation Parameters for LLM Translation.
Next, you'll configure your translation prompt and optionally enable Retrieval-Augmented Generation (RAG) to further enhance translations, then test the output.
Step 4: Use the LLM Profile to translate content
Once created, the LLM Profile can be used within Smartling in a translation workflow or with one of Smartling's instant MT integrations. For details, see Use an LLM Profile to translate content.
Troubleshooting Grok (xAI) translation issues
Error appears on the Profile page in the AI Hub
- Check whether you've exceeded xAI's rate limits or your account's usage/billing limits
- Confirm your API key is still valid and hasn't been revoked in the xAI Console
- Verify the model name entered in the profile matches a currently available text/chat model
Translations aren't appearing
- Verify the LLM Profile has been added to your workflow's translation step or selected for your instant MT integration
- Check for error messages on the Profiles page in the AI Hub
- Confirm your fallback provider is working, if one is configured
Poor translation quality
- Review and refine your translation prompt
- Try a different Grok model
- Consider adding a human review step to your workflow
Considerations
Compared to traditional machine translation providers, LLMs like xAI's Grok models provide more flexibility, but also come with tradeoffs worth understanding before you rely on them for production translation.
Read about important considerations for translating with LLMs in Translating with LLMs in Smartling.