xAI

Overview

xAI is an OpenAI-compatible provider powering the Grok family of models. Use it through DeepIntShield with the standard OpenAI-compatible request format. Key features:

Full OpenAI compatibility - Chat, text completion, and responses
Vision support - Image URLs and base64 encoding for multimodal models
Streaming support - Server-Sent Events with delta-based updates
Reasoning support - Extended thinking for Grok reasoning models
Tool calling - Complete function definition and execution
Parameter filtering - Removes unsupported OpenAI-specific fields

Supported Operations

Operation	Non-Streaming	Streaming	Endpoint
Chat Completions	✅	✅	`/v1/chat/completions`
Responses API	✅	✅	`/v1/responses`
Text Completions	✅	✅	`/v1/completions`
Image Generation	✅	-	`/v1/images/generations`
List Models	✅	-	`/v1/models`
Embeddings	❌	❌	-
Speech (TTS)	❌	❌	-
Transcriptions (STT)	❌	❌	-
Files	❌	❌	-
Batch	❌	❌	-

1. Chat Completions

Request Parameters

xAI supports all standard OpenAI chat completion parameters. For full parameter reference and behavior, see OpenAI Chat Completions.

The following parameters are not supported by xAI and are ignored: prompt_cache_key, verbosity, store, service_tier.

Reasoning Support

grok-4.5 and grok-4.6 accept explicit reasoning effort; grok-4.6 also supports xhigh. Reasoning cannot be disabled on these models. See xAI’s reasoning guide.

{
  "model": "xai/grok-4.6",
  "messages": [{"role": "user", "content": "Explain the reasoning."}],
  "reasoning_effort": "high"
}

DeepIntShield preserves effort for these models and legacy Grok 3 Mini. Older Grok 4 models retain their existing compatibility filtering.

Vision Support

xAI vision models support both image URLs and base64-encoded images:

{
  "model": "xai/grok-2-vision-1212",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "What is in this image?"},
      {"type": "image_url", "image_url": {"url": "https://..."}}
    ]
  }]
}

Supported Image Formats:

✅ Image URLs
✅ Base64-encoded images
✅ Multiple images per message

xAI supports all standard OpenAI message types, tools, responses, and streaming formats. For details on message handling, tool conversion, responses, and streaming, refer to OpenAI Chat Completions.

2. Responses API

xAI exposes a native Responses API at /v1/responses. It uses input, max_output_tokens, reasoning, and flat function-tool fields, with JSON and SSE output. Encrypted reasoning state is preserved for current Grok reasoning models, including tool continuations. Playground prefers Responses for bundled Grok 4.5, Grok 4.6, and Grok 4.20 multi-agent profiles and retains output items in saved sessions.

3. Text Completions

xAI supports legacy text completion format:

Parameter	Mapping
`prompt`	Direct pass-through
`max_tokens`	max_tokens
`temperature`, `top_p`	Direct pass-through
`stop`	Stop sequences
`frequency_penalty`, `presence_penalty`	Penalty parameters

Streaming support available via stream: true.

4. Image Generation

xAI’s image generation uses the OpenAI-compatible format.

Request Behavior

xAI uses the same request format as OpenAI (see OpenAI Image Generation). Your model, prompt, and all other parameters are passed through in OpenAI format.

Endpoint: /v1/images/generations

Response Behavior

Responses are returned as-is in the DeepIntShield image-generation response format.

Streaming: Image generation streaming is not supported by xAI.

5. List Models

Lists available xAI models with their capabilities and context lengths.

Unsupported Features

Feature	Reason
Embedding	Not offered by xAI API
Speech/TTS	Not offered by xAI API
Transcription/STT	Not offered by xAI API
Batch Operations	Not offered by xAI API
File Management	Not offered by xAI API