Hormouz AIHormouzSign in

SpaceXAI: Grok 4.6: AI model

Grok 4.6 is a frontier Grok model for coding, knowledge work and STEM from SpaceXAI with a 500K-token context window. Reachable from inside Iran through Hormouz.

Context window:
500,000 tokens
Input:
$2/1M tokens
Output:
$6/1M tokens
Type:
text, image
  • Vision
  • Tools
  • Streaming
  • Long context

Thinking levels: Always thinks · xhigh · high · medium · low

Grok 4.6 is a SpaceXAI model with frontier-level results in coding, knowledge work and science, technology, engineering and maths. It reads text, images and PDFs over a 500K-token context and always reasons, with effort from low to xhigh. It has been succeeded by Grok 4.7, which is stronger on long software tasks.

It accepts text, image and file (PDF) input and returns text, and supports tool calling, structured JSON output and streaming. It always reasons before answering, and you choose how hard it thinks with the reasoning effort setting. Grok 4.6 is commonly used for coding, STEM problem solving, knowledge work and analysis of documents and images. Hormouz serves it behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs without changes.

Pricing is usage-based: $2 per million input tokens and $6 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "x-ai/grok-4.6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorxAI
TypeText, Image
Context window500,000 tokens
Pricing$2.00/M in · $6.00/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

44.3
Intelligence Index
Better than 87% of models we compared
76.8
Coding Index
Better than 96% of models we compared
53
Agentic Index
Better than 95% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
94.9%
HLE
Humanity's Last Exam
42.9%
AA-LCR
Long-context reasoning
80.3%
CritPt
Research-level physics reasoning
17.1%
AA Omniscience
Broad factual knowledge accuracy
48.2%
Non-Hallucination
Rate of avoiding fabricated answers
65.7%

Coding

SciCode
Python for scientific computing
56.5%

Agentic

GDPval
Economically valuable tasks
56.1%

Source: Artificial Analysis

Agentic Game Dev
Top 37%
1,210Elo
Win rate: 47.1%
Android Native
Top 3%
1,303Elo
Win rate: 61.3%
Full-Stack
Top 18%
1,263Elo
Win rate: 54.9%
Godot Game Dev
Top 11%
1,276Elo
Win rate: 53%
HTML Slides
Top 13%
1,249Elo
Win rate: 60.1%
Mobile Apps
Top 15%
1,233Elo
Win rate: 55.8%
Python Slides
Top 30%
1,242Elo
Win rate: 52.7%
Web Apps
Top 24%
1,241Elo
Win rate: 56%
3D
Top 12%
1,288Elo
Win rate: 52.6%Avg time: 233s
ASCII Art
Top 11%
1,285Elo
Win rate: 57.7%Avg time: 164s
Code
Top 9%
1,298Elo
Win rate: 52.8%Avg time: 276s
Data Viz
Top 10%
1,294Elo
Win rate: 52%Avg time: 203s
Game Dev
Top 10%
1,307Elo
Win rate: 54.2%Avg time: 322s
SVG
Top 15%
1,243Elo
Win rate: 49.5%Avg time: 233s
UI Component
Top 13%
1,294Elo
Win rate: 52.6%Avg time: 241s
Website
Top 9%
1,298Elo
Win rate: 52.6%Avg time: 316s

Metrics sourced from Design Arena

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "x-ai/grok-4.6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="x-ai/grok-4.6",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "x-ai/grok-4.6",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the SpaceXAI: Grok 4.6 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches SpaceXAI: Grok 4.6 and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Grok 4.6 cost?
Pricing is usage-based: $2 per million input tokens and $6 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use.
How do I access Grok 4.6 from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Grok 4.6 compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What context window and capabilities does Grok 4.6 have?
It has a 500K-token context window, accepts text, image and file (PDF) input, and supports tool calling, structured JSON output and streaming. It always reasons before answering, and you choose how hard it thinks with the reasoning effort setting.
What is Grok 4.6 good for?
Typical uses are coding, STEM problem solving, knowledge work and analysis of documents and images.

Updated 2026-10-13