Grok 4.6 costs $4 per million input tokens and $12 per million output tokens on Roar AI. xAI’s flagship from August 2026, strongest at graduate-level science questions.
Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $24. Every rate is published and stays the same from one request to the next. See every model.
Rates as of 20 November 2026.
grok-4.6Grok 4.6 is xAI’s flagship for code and general work. Its strongest result is 94.9% on GPQA Diamond, a test of graduate-level science questions, which independent rankings put first of hundreds of models. It also made a big jump over Grok 4.5 on agent-style office work, and xAI highlights turning a rough description into a working software prototype.
On an independent test of made-up answers, its rate fell from 54% to 34%. That is better, but still about one wrong answer in three on that test, so keep a check on anything a customer sees. Its context window is 500K tokens, half that of the million-token models.
Use the OpenAI SDK you already have: point it at Roar AI and set the model name. Read the docs.
from openai import OpenAI
client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")
reply = client.chat.completions.create(
model="grok-4.6",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Input is $4 per 1M tokens; output is $12 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $24.
Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from Grok 4.6 to another model only means changing the model name in your code.
No. xAI does not publish the weights, so it is only available through an API like this one.
Grok 4.6 can read up to 500K tokens in one request.
It reads images directly. You can still send it a PDF: Roar AI turns each page into text first, at no extra charge.
Create a free account, get an API key and call Grok 4.6 with the OpenAI SDK.