SpaceXAI: Grok 4.20: AI model
Grok 4.20 is xAI's fast reasoning model with agentic tool calling, a very low hallucination rate and a 2M-token context window. Reachable from inside Iran through Hormouz.
- Context window:
- 2,000,000 tokens
- Input:
- $1.25/1M tokens
- Output:
- $2.5/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Thinking levels:
Grok 4.20 is a reasoning model from xAI built for speed and agentic tool use. It pairs strict prompt adherence with a very low hallucination rate, so it returns precise, well-grounded answers, and it can call tools to drive multi-step workflows. Reasoning can be turned on or off per request via the API.
It accepts text and image input and returns text, and it supports a large 2M-token context window. Enough for entire codebases, long document sets and extended agent sessions. Tool calling and structured output make it a strong backbone for autonomous assistants, coding agents and data pipelines.
Through Hormouz, Grok 4.20 is served behind an OpenAI-compatible API and reachable from inside Iran without a foreign credit card or circumvention tooling. Billing is usage-based at $1.25 per million input tokens and $2.50 per million output tokens.
Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
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-4.20",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | xAI |
|---|---|
| Type | Text, Image |
| Context window | 2,000,000 tokens |
| Pricing | $1.25/M in · $2.50/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
Benchmarks
Reasoning
Coding
Agentic
Source: Artificial Analysis
Design Arena
How Design Arena works ↗Ranking distribution
6703 tournaments ?
Metrics sourced from Design Arena
Code example
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-4.20",
"messages": [{"role": "user", "content": "Hello!"}]
}'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-4.20",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)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-4.20",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the SpaceXAI: Grok 4.20 API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches SpaceXAI: Grok 4.20 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.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Grok 4.20 cost?
- Billing is usage-based: $1.25 per million input tokens and $2.5 per million output tokens. There is no monthly minimum. You pay only for the tokens you actually use.
- How do I access Grok 4.20 from inside Iran?
- Create a Hormouz account, generate an API key and point your client at Hormouz. Access to Grok 4.20 is served from inside Iran, so you do not need a foreign credit card, a VPN or any sanction-circumvention tooling.
- Is Grok 4.20 compatible with the OpenAI SDK?
- Yes. Hormouz exposes an OpenAI-compatible chat-completions API. Change the base URL to Hormouz and drop in your Hormouz key, and existing OpenAI SDK code runs unchanged.
- What context window does Grok 4.20 support?
- Grok 4.20 supports a context window of up to 2M tokens, which is enough for long documents and extended conversations in a single request.
- Can I turn Grok 4.20's reasoning on and off?
- Yes. Reasoning is controllable per request through the API. You can enable it for hard, multi-step problems or disable it for faster, cheaper responses on simple tasks.
- Does Grok 4.20 support tools and images?
- Yes. It supports agentic tool calling and structured output, and it accepts image input alongside text. That makes it suitable for coding agents, automation and multimodal assistants.
Updated 2026-10-13