xAI: Grok 4.6

grok-4.6

xAI Grok 4.6 is a frontier multimodal reasoning model focused on long-running agents, coding, knowledge work, and interactive visual work.

chattextvisionxaigrokreasoningcodingagentictoolsstructured-outputcaching

Connection

When calling through the Token360 unified gateway, use the Base URL, path, and model id below, no per-vendor endpoint hunting.

Base URL

https://api.token360.ai/v1

Endpointchat/completions

Model id

grok-4.6

Capabilities & limits

Model type: Vision Language
Input modalities
Output modalities
Context: 500,000tokens
Max output: 500,000tokens
Vision / images: Yes
Tools & function calling: Not specified

Updated Aug 12, 2026

Pricing

Pay as you go. Rates depend on the provider route you use; below is reference pricing when available.

Input tokens

Up to 200K
- Input tokens
  Input tokens minus Cache hit tokens, then billed
  $2 / per 1M tokens
- Cache hit tokens
  $0.5 / per 1M tokens
- Output tokens
  $6 / per 1M tokens
200K or more
- Input tokens
  Input tokens minus Cache hit tokens, then billed
  $4 / per 1M tokens
- Cache hit tokens
  $1 / per 1M tokens
- Output tokens
  $12 / per 1M tokens

One scenario is selected per request; prices from different rows are not added together. Within the selected scenario, the listed meter charges are added together. For adjusted meters, the named sub-meters are deducted before applying the rate.