xAI provider

Related Documentation
Minimum Version
AI Gateway - 2.0
Incompatible with
on-prem
Tags
#ai
Previous Versions of this page

You can proxy requests to xAI AI models through AI Gateway by creating AI Model Provider and AI Model entities. This reference documents all supported AI capabilities, configuration requirements, and provider-specific details needed for proper integration.

Upstream paths

AI Gateway automatically routes requests to the appropriate xAI API endpoints. The following table shows the upstream paths used for each capability.

Capability

Path template

Description

Upstream path or API

Generate /chat/completions, /completions, or /responses Text generation for chat completions and responses /v1/chat/completions
Agentic /assistants or /responses Agent and assistant-based interactions /v1/responses
Image /images/generations or /images/edits Image generation and editing /v1/images/generations

Supported capabilities

The following tables show the AI capabilities supported by the xAI provider when configuring AI Models.

By default, AI Gateway uses the path templates shown in the tables below (e.g., /chat/completions, /embeddings, etc.). To customize these paths, configure the config.paths field in your AI Model entity. Custom paths take the form {configured_path}/{template_path} — for example, if you set a custom path of /v2, requests to /embeddings would be routed to /v2/embeddings.

Text generation

Support for xAI text generation capabilities:

Capability

Streaming

Model example

Path template

Min version

generate Not supported grok-3 /chat/completions, /completions, or /responses 2.0

Agentic

Support for xAI agent and assistant capabilities:

Capability

Model example

Path template

Min version

agentic grok-3 /assistants or /responses 2.0

Image

Support for xAI image generation and editing capabilities:

Capability

Model example

Path template

Min version

image grok-2-image /images/generations or /images/edits 2.0

For requests with large payloads, consider increasing config.max_request_body_size on your AI Model entity to three times the raw binary size.

Supported image sizes and formats vary by model. Refer to your provider’s documentation for allowed dimensions and requirements.

xAI base URL

The base URL is https://api.x.ai:443/{capability_path}. The {capability_path} is determined by the AI capability.

AI Gateway uses this URL automatically. You only need to configure a URL if you’re using a self-hosted or xAI-compatible endpoint, in which case set the upstream_url option in your AI Model configuration.

Configure xAI

To use xAI with AI Gateway, configure a new AI Model Provider. You can then access supported AI Models from xAI.

Here’s a minimal configuration for chat completions:

Help us make these docs great!

Kong Developer docs are open source. If you find these useful and want to make them better, contribute today!