xAINew

Grok 4.5 API

Fast frontier reasoning with live search

xAI's flagship, with optional realtime web and social search grounded into the answer.

ChatTool useStreaming256K context

Quickstart

Authenticate with a bearer token from your dashboard, then POST the request below.

curl -X POST https://api.viddly.io/v1/chat/completions \
  -H "Authorization: Bearer $VIDDLY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4-5",
    "messages": [
      {
        "role": "user",
        "content": "Explain retrieval augmented generation in two sentences."
      }
    ],
    "max_tokens": 512
  }'

Parameters

Name	Type	Default	Description
messages*	text	—	Chat messages array, OpenAI-compatible.
max_tokens	number	1024	Upper bound on generated tokens.
temperature	number	0.7	Sampling temperature, 0–2.
stream	boolean	false	Stream tokens as server-sent events.