Keep the OpenAI Chat Completions format. Change the base URL, use your ZeroFA key, and send the live model ID.
The public catalog identifies Grok 4.3 as a xAI text model.
Model replies will appear here
Use the runtime base URL and the selected live catalog model ID.
curl https://zerofa.ai/v1/chat/completions \
-H "Authorization: Bearer $ZEROFA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-4.3",
"messages": [
{ "role": "user", "content": "Write a concise product launch brief." }
]
}'import OpenAI from "openai"
const client = new OpenAI({
apiKey: process.env.ZEROFA_API_KEY,
baseURL: "https://zerofa.ai/v1",
})
const response = await client.chat.completions.create({
model: "grok-4.3",
messages: [
{ role: "user", content: "Write a concise product launch brief." },
],
})import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["ZEROFA_API_KEY"],
base_url="https://zerofa.ai/v1",
)
response = client.chat.completions.create(
model="grok-4.3",
messages=[
{"role": "user", "content": "Write a concise product launch brief."}
],
)Use the same base URL, API key, and model ID in tools that support a custom OpenAI-compatible provider.
Prices come from the live public catalog and are shown per 1M tokens. Select a row to update the examples above.