xAIPaidOperational

Grok 4.20 Reasoning

API model name: grok-4-20-reasoning

Grok 4.20 Reasoning is xAI's chat model, served on the Api.Airforce unified API. Capabilities include Reasoning. It is priced at $0.27 per million input tokens and $0.81 per million output tokens. Access it through the OpenAI-compatible API with one key, alongside 100+ other models on Api.Airforce.

Get an API key View pricing

Pricing

Input / 1M tokens

$0.27

Output / 1M tokens

$0.81

Cache read / 1M tokens

$0.03

Specifications

Provider: xAI
Type: chat model

Capabilities

Reasoning

What is Grok 4.20 Reasoning used for?

Chatbots & assistants — conversational AI, drafting, summarizing and Q&A.
Complex reasoning — math, coding and step-by-step problem solving.

Grok 4.20 Reasoning vs. similar models

Model	Intelligence	Context	Input / 1M	Output / 1M
Grok 4.20 Reasoning	—	—	$0.27	$0.81
Grok 2 Vision	—	—	$3.12	$15.57
Grok 3	18.4	—	$2.91	$14.55
Grok 3 Deepsearch	—	—	$0.57	$2.89

Prices are Api.Airforce pay-as-you-go rates per 1M tokens. Context is the maximum input length.

Related models

Grok 2 VisionxAI · $3.12 / 1M Grok 3xAI · $2.91 / 1M Grok 3 DeepsearchxAI · $0.57 / 1M Grok 3 FastxAI · $4.74 / 1M Grok 3 MinixAI · $0.51 / 1M Grok 3 Mini FastxAI · $0.93 / 1M Grok 3 ReasonerxAI · $0.57 / 1M Grok 4xAI · $1.64 / 1M Grok 4xAI · $2.07 / 1M Grok 4 FastxAI · $0.20 / 1M Grok 4 Fast ReasoningxAI · $0.02 / 1M Grok 4.1 FastxAI · $0.15 / 1M

Grok 4.20 Reasoning — frequently asked questions

How much does Grok 4.20 Reasoning cost?: Grok 4.20 Reasoning is billed pay-as-you-go at $0.27 per 1M input tokens and $0.81 per 1M output tokens. There is no subscription — you only pay for what you use.
What can Grok 4.20 Reasoning do?: Grok 4.20 Reasoning supports Reasoning.
Is Grok 4.20 Reasoning free to use?: Grok 4.20 Reasoning is a paid, pay-as-you-go model — no subscription, you are only charged for usage.
How do I use Grok 4.20 Reasoning via the API?: Grok 4.20 Reasoning is OpenAI-compatible. Point any OpenAI SDK at https://api.airforce/v1 and pass the model ID grok-4-20-reasoning with your Api.Airforce API key.
Who makes Grok 4.20 Reasoning?: Grok 4.20 Reasoning is xAI's chat model, served through the unified Api.Airforce gateway alongside 100+ other models.

All models·Quickstart·Chat API reference

Use Grok 4.20 Reasoning via the API

OpenAI-compatible — point any OpenAI SDK at https://api.airforce/v1 and pass grok-4-20-reasoning as the model.

cURL

curl https://api.airforce/v1/chat/completions \
  -H "Authorization: Bearer $AIRFORCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4-20-reasoning",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Python

from openai import OpenAI
client = OpenAI(base_url="https://api.airforce/v1", api_key="$AIRFORCE_API_KEY")
r = client.chat.completions.create(
    model="grok-4-20-reasoning",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airforce/v1", apiKey: process.env.AIRFORCE_API_KEY });
const r = await client.chat.completions.create({
  model: "grok-4-20-reasoning",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(r.choices[0].message.content);