feat: added xai provider in ui and docs (#1236)

## Add xAI Provider Support

Added support for the xAI provider, which powers the Grok family of models. This integration enables users to access Grok models through Bifrost with full OpenAI compatibility.

## Changes

- Added xAI provider documentation with detailed operation support
- Updated provider overview table to include xAI capabilities
- Added xAI to the model provider enum in OpenAPI schema
- Added UI support with model placeholders and provider icon
- Added xAI to known providers list for logging

## Type of change

- [x] Feature
- [x] Documentation

## Affected areas

- [x] Providers/Integrations
- [x] UI (Next.js)
- [x] Docs

## How to test

1. Configure an xAI API key in your environment
2. Make requests to supported endpoints with xAI models:

```sh
# Chat completion example
curl -X POST http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xai/grok-3-mini",
    "messages": [{"role": "user", "content": "Hello, how are you?"}]
  }'

# Test vision capabilities with Grok vision models
curl -X POST http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "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://example.com/image.jpg"}}
      ]
    }]
  }'
```

## Breaking changes

- [x] No

## Related issues

Implements provider support requested in issue tracker

## Checklist

- [x] I added/updated tests where appropriate
- [x] I updated documentation where needed
- [x] I verified builds succeed (Go and UI)

Author: akshaydeo

docs/docs.json

@@ -107,7 +107,8 @@
                   "providers/supported-providers/parasail",
                   "providers/supported-providers/perplexity",
                   "providers/supported-providers/sgl",
-                  "providers/supported-providers/vertex"
+                  "providers/supported-providers/vertex",
+                  "providers/supported-providers/xai"
                 ]
               },
               "providers/reasoning",

docs/openapi/schemas/inference/common.yaml

@@ -22,6 +22,7 @@ ModelProvider:
     - elevenlabs
     - huggingface
     - nebius
+    - xai
 
 Fallback:
   type: object

docs/providers/supported-providers/overview.mdx

@@ -35,6 +35,7 @@ The following table summarizes which operations are supported by each provider v
 | Perplexity (`perplexity/<model>`) | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
 | SGL (`sgl/<model>`) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
 | Vertex AI (`vertex/<model>`) | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ |
+| xAI (`xai/<model>`) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
 
 
 - 🟡 Not supported by the downstream provider, but internally implemented by Bifrost as a fallback.

docs/providers/supported-providers/xai.mdx

@@ -0,0 +1,139 @@
+---
+title: "xAI"
+description: "xAI API conversion guide - OpenAI-compatible format, Grok models, vision support, reasoning, and parameter handling"
+icon: "x"
+---
+
+## Overview
+
+xAI is an **OpenAI-compatible provider** powering the Grok family of models. Bifrost delegates to the OpenAI implementation with standard parameter filtering. 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` |
+| List Models | ✅ | - | `/v1/models` |
+| Embeddings | ❌ | ❌ | - |
+| Speech (TTS) | ❌ | ❌ | - |
+| Transcriptions (STT) | ❌ | ❌ | - |
+| Files | ❌ | ❌ | - |
+| Batch | ❌ | ❌ | - |
+
+<Note>
+**Unsupported Operations** (❌): Embeddings, Speech, Transcriptions, Files, and Batch are not supported by the upstream xAI API. These return `UnsupportedOperationError`.
+</Note>
+
+---
+
+# 1. Chat Completions
+
+## Request Parameters
+
+xAI supports all standard OpenAI chat completion parameters. For full parameter reference and behavior, see [OpenAI Chat Completions](/providers/supported-providers/openai#1-chat-completions).
+
+### Filtered Parameters
+
+Removed for xAI compatibility:
+- `prompt_cache_key` - Not supported
+- `verbosity` - Anthropic-specific
+- `store` - Not supported
+- `service_tier` - Not supported
+
+### Reasoning Support
+
+xAI's `grok-3-mini` model supports extended reasoning via the standard `reasoning_effort` field:
+
+```json
+{
+  "model": "xai/grok-3-mini",
+  "messages": [...],
+  "reasoning_effort": "high"
+}
+```
+
+<Warning>
+**Model-Specific Feature**: The `reasoning_effort` parameter is only supported by `grok-3-mini`. Other Grok-3 and Grok-4 models will return an error if this parameter is specified.
+</Warning>
+
+Bifrost converts from the internal `Reasoning` structure to xAI's `reasoning_effort` string format.
+
+### Vision Support
+
+xAI vision models support both image URLs and base64-encoded images:
+
+```json
+{
+  "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](/providers/supported-providers/openai#1-chat-completions).
+
+---
+
+# 2. Responses API
+
+xAI's Responses API is forwarded directly to `/v1/responses`:
+
+```
+ResponsesRequest → /v1/responses → ResponsesResponse
+```
+
+Same parameter support and message handling as Chat Completions. Full streaming support available.
+
+---
+
+# 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. 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 |
+
+---

transports/changelog.md

@@ -1,2 +1,3 @@
 - fix: added missing logs filter checks in ui for live updates
-- fix: ensure request ID is consistently set in context before PreHooks are executed
+- fix: ensure request ID is consistently set in context before PreHooks are executed
+- docs: updated docs for xai provider

ui/lib/constants/config.ts

@@ -47,7 +47,8 @@ export const ModelPlaceholders = {
 	ollama: "e.g. llama3.1, llama2",
 	openai: "e.g. gpt-4, gpt-4o, gpt-4o-mini, gpt-3.5-turbo",
 	vertex: "e.g. gemini-1.5-pro, text-bison, chat-bison",
-	nebius: "e.g. openai/gpt-oss-120b, google/gemma-2-9b-it-fast, Qwen/Qwen2.5-VL-72B-Instruct"
+	nebius: "e.g. openai/gpt-oss-120b, google/gemma-2-9b-it-fast, Qwen/Qwen2.5-VL-72B-Instruct",
+	xai: "e.g. grok-4-0709, grok-3-mini, grok-3, grok-2-vision-1212",
 };
 
 export const isKeyRequiredByProvider: Record<ProviderName, boolean> = {
@@ -69,6 +70,7 @@ export const isKeyRequiredByProvider: Record<ProviderName, boolean> = {
 	vertex: true,
 	perplexity: true,
 	nebius: true,
+	xai: true,
 };
 
 export const DefaultNetworkConfig = {

ui/lib/constants/icons.tsx

@@ -605,6 +605,25 @@ export const ProviderIcons = {
 	nebius: ({ size = "md", className = "" }: IconProps) => {
 		return <img src="/images/nebius.jpeg" alt="Nebius" className={className} />;
 	},
+	xai: ({ size = "md", className = "" }: IconProps) => {
+		const resolvedSize = resolveSize(size);
+
+		return (
+			<svg
+				fill="currentColor"
+				fillRule="evenodd"
+				height={resolvedSize}
+				style={{ flex: "none", lineHeight: "1" }}
+				viewBox="0 0 24 24"
+				width={resolvedSize}
+				xmlns="http://www.w3.org/2000/svg"
+				className={className}
+			>
+				<title>Grok</title>
+				<path d="M6.469 8.776L16.512 23h-4.464L2.005 8.776H6.47zm-.004 7.9l2.233 3.164L6.467 23H2l4.465-6.324zM22 2.582V23h-3.659V7.764L22 2.582zM22 1l-9.952 14.095-2.233-3.163L17.533 1H22z"></path>
+			</svg>
+		);
+	},
 } as const;
 
 // Helper component to render provider icons

ui/lib/constants/logs.ts

@@ -18,6 +18,7 @@ export const KnownProvidersNames = [
 	"sgl",
 	"vertex",
 	"nebius",
+	"xai",
 ] as const;
 
 // Local Provider type derived from KNOWN_PROVIDERS constant
@@ -61,6 +62,7 @@ export const ProviderLabels: Record<ProviderName, string> = {
 	openrouter: "OpenRouter",
 	huggingface: "HuggingFace",
 	nebius: "Nebius Token Factory",
+	xai: "xAI",
 } as const;
 
 // Helper function to get provider label, supporting custom providers