xaiavailablesupports_audio_inputsupports_function_callingsupports_reasoningsupports_response_schemasupports_tool_choicesupports_visionsupports_web_search

Back to Model Explorer

xAIAvailable on AvalAI

grok-4.20-beta-0309-reasoning API on AvalAI

grok-4.20-beta-0309-reasoning

grok-4.20-beta-0309-reasoning is an AI model from xAI that is available through AvalAI's OpenAI-compatible API.

Open dashboardCompare

Price display scale

Input price$2.00 / 1M tokens

Output price$6.00 / 1M tokens

Context window20,000,000 tokens

Maximum output2,000,000 tokens

Use grok-4.20-beta-0309-reasoning with the AvalAI API

Keep the API key in an environment variable and send requests from server-side code.

Bash

curl https://api.avalai.ir/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AVALAI_API_KEY" \
  -d '{"model": "grok-4.20-beta-0309-reasoning", "messages": [{"role": "user", "content": "Give a concise, practical solution."}]}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AVALAI_API_KEY"],
    base_url="https://api.avalai.ir/v1",
)

response = client.chat.completions.create(
    model="grok-4.20-beta-0309-reasoning",
    messages=[{"role": "user", "content": "Give a concise, practical solution."}],
)

print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AVALAI_API_KEY,
  baseURL: "https://api.avalai.ir/v1",
});

const response = await client.chat.completions.create({
  model: "grok-4.20-beta-0309-reasoning",
  messages: [{ role: "user", content: "Give a concise, practical solution." }],
});

console.log(response.choices[0].message.content);

Create an API keyRead the quickstart

Capabilities and endpoints

• audio_input
• function_calling
• reasoning
• response_schema
• tool_choice
• vision
• web_search

grok-4.20-beta-0309-reasoning rate limits

Tier	RPM	TPM
0	1	40,000
1	5	80,000
2	10	100,000
3	15	150,000
4	25	200,000
5	30	400,000

Related models

• grok-4.20-beta-0309-non-reasoning
• grok-4.20-reasoning
• grok-4.20-non-reasoning
• Grok 4.5

Frequently asked questions

What is the grok-4.20-beta-0309-reasoning API on AvalAI?

Create an AvalAI API key and send the model ID grok-4.20-beta-0309-reasoning to one of the supported endpoints shown on this page.

How much does the grok-4.20-beta-0309-reasoning API cost on AvalAI?

The grok-4.20-beta-0309-reasoning API on AvalAI costs $2.00 per 1M input tokens and $6.00 per 1M output tokens.

What is the token cost for grok-4.20-beta-0309-reasoning?

Current AvalAI pricing for grok-4.20-beta-0309-reasoning is $2.00 / 1M tokens for input and $6.00 / 1M tokens for output.

What is the grok-4.20-beta-0309-reasoning context window?

The recorded maximum input context for grok-4.20-beta-0309-reasoning is 20,000,000 tokens.

Third-party data and freshness

• Pricing, availability, endpoints, and rate limits: AvalAI structured data (authoritative)