Grok

Grok 4.6

Chat
Not available
Get started

xAI's frontier model for long-running agents, coding, research, and interactive/visual work. Text and image input, text-only output.

Context
500Ktokens
Max output
Unlimitedtokens
Latency
~14ms
Released
2026-08-12

Pricing

$ / 1M tokens
Input
$2.00/M
Output
$6.00/M
Cache Read
$0.50/M
Cache Write
$2.00/M

Capabilities

3 listed
  • Chat
  • Tool Use
  • Coding

Code examples

POST /v1/chat/completions
python
from openai import OpenAI

client = OpenAI(
    api_key="your_api_key",
    base_url="https://api.modelstack.cc/v1",
)

response = client.chat.completions.create(
    model="grok-4.6",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Related models

Frequently asked questions

How is Grok 4.6 billed on ModelStack?expand_more
ModelStack bills based on actual request usage. Input, output, cache, and any other applicable rates follow the live pricing table on this page. Final request costs are available in the console.
What are the context window and maximum output for Grok 4.6?expand_more
Grok 4.6 has a 500K context window and supports up to Unlimited of output.
How can I call Grok 4.6 through ModelStack?expand_more
Use the model ID `grok-4.6` with any OpenAI-compatible SDK pointed at the ModelStack API — see the code examples above for Python, Node.js, and cURL.
Which capabilities does Grok 4.6 support?expand_more
Grok 4.6 supports: Chat, Tool Use, Coding.