Grok 4.7

Grok 4.7 (x-ai/grok-4.7) — an xAI model: strong code, fast reasoning, native web search with fresh news. Accepts images and files; reasoning depth is controllable from low to xhigh and cannot be turned off.

Parameters and capabilities

Parameter	Value
model	x-ai/grok-4.7 (short alias grok-4.7)
reasoning_effort	low, medium, high, xhigh
Disabling reasoning	no — the model always thinks
Images on input	yes (image_url, data URLs)
Files on input	yes (PDF/DOCX/TXT etc., up to 5)
Web search	native (web_search: "native"); $0.006 per performed request
Cache read	$0.63 per 1M tokens

Example

curl https://api.mixen.ai/v1/chat/completions \
  -H "Authorization: Bearer $MIXEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "x-ai/grok-4.7",
    "web_search": "native",
    "messages": [{"role": "user", "content": "What did xAI ship this week? With sources"}]
  }'

Pricing

Per 1M tokens: input $2.50, output $7.50, cache read $0.63. Web search — $0.006 per performed request (the model decides whether to search). Current prices — catalog.

Strengths and limitations

• Native web search — fresh events and news; billed per performed request, not per token.
• Reasoning is always on; its tokens are billed.
• Reasoning eats max_tokens — set a generous ceiling for long answers.

All models — in the catalog. Web search — guide; the general workflow — chat guide.