xAI: Grok 4.6
Grok 4.6 is a model from SpaceXSI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.
- Input
- 720,776 Toman/M tokens
- Output
- 2,162,328 Toman/M tokens
- Context
- 500K
- Max output
- 450K
- Published
- Aug 12, 2026
- Maker
- xAI
Free plan prices, in Toman at today's rate. Plans and prices
Price by plan
Toman per million tokens at today's rate. A plan lowers the price of your usage up to a limit each period. Up to 200K tokens.
| Plan | Input | Output |
|---|---|---|
| Free | 720,776 | 2,162,328 |
| Pro | 691,236 | 2,073,708 |
| Max | 661,696 | 1,985,088 |
Long prompts
This model costs more when a request's prompt is long: once the prompt reaches the size below, the whole request is billed at the higher price (as its provider bills it). Toman per million tokens, per plan.
| Plan | Input | Output |
|---|---|---|
| Free | 1,441,552 | 4,324,656 |
| Pro | 1,382,472 | 4,147,416 |
| Max | 1,323,392 | 3,970,176 |
Capabilities
- Text
- Vision
- Tools
- JSON
- Reasoning
What it takes and gives
- Text
- Image
- File (PDF)
- Text
Every input listed here works through the API and the playground: images and PDFs as data URLs or https links, audio as base64, video as a data URL or a link the model supports.
Call it
Pass x-ai/grok-4.6 as the model name, or let router/auto choose for you.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://ai.fluxcdn.cloud/api/v1",
api_key=os.environ["FLUXCDN_API_KEY"],
)
resp = client.chat.completions.create(
model="router/auto",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
