Grok 4.6

spacexai/grok-4.6

A chat model with a 500K-token context window, at $2.10 per million input tokens and $6.30 per million output tokens.

Details

Maker
spacexai
Kind
Chat
Context window
500,000 tokens
Max output
500,000 tokens
Input
$2.10 per million tokens
Cached input
$0.525 per million tokens, 75% off
Cache write
Same as input
Output
$6.30 per million tokens
Capabilities
Reasoning, tool use, vision
Takes
Text, image
Returns
Text
Zero data retention
Yes, on every provider
No training on requests
Yes, on every provider
Released
2026-08-12
Newer model
spacexai/grok-4.7Released later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

Grok 4.6 builds on Grok 4.5 with a particular focus on long-running agents and more ambitious interactive and visual work. It stays with complex tasks across many steps, whether researching a topic, analyzing information, working across a codebase, or turning an idea into a polished application or work artifact.

Call it

curl
curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "spacexai/grok-4.6",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.