xAI · live catalog

Grok 4.20 (Non-Reasoning) API

model: grok-4.20-0309-non-reasoning

This model is not available on the CallAI gateway yet; prices shown are the official reference. See the model directory for available models in the same family.

Grok model for agentic tool use, reasoning, coding, and live assistance

CallAI pricing

Crypto OK

Input / 1M:$1.38

Output / 1M:$2.75

Specs & upstream

Upstream (in/out):$1.25 / $2.50

Context:1M

Not callable yet

Grok 4.20 (Non-Reasoning) is not live on the CallAI gateway yet. The code below will work once it is listed; calling it now returns model_not_available. Please don't top up for this model: USDT top-ups are non-refundable once credited (details). See the model directory for available models in the same family.

SDK quickstart

OpenAI-compatible

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-live-your-callai-key",
    base_url="https://api.callaiapi.com/v1"
)

response = client.chat.completions.create(
    model="grok-4.20-0309-non-reasoning",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Hello, explain quicksort with Python"}
    ],
    stream=True
)

for chunk in response:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

Node.js / TypeScript

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: process.env.CALLAI_API_KEY,
  baseURL: 'https://api.callaiapi.com/v1',
});

const response = await openai.chat.completions.create({
  model: 'grok-4.20-0309-non-reasoning',
  messages: [{ role: 'user', content: 'Hello!' }],
  stream: true,
});

for await (const chunk of response) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}