OpenAI-compatible gateway

Use OpenAI models through APIXO

Keep the OpenAI SDK and request format. Change the baseURL, use your APIXO key, and choose any OpenAI model ID from the table.

Base URL

https://llm.apixo.ai/v1

API key

APIXO_API_KEY

Model ID

gpt-5.4

Official SDK quick start

The request body stays provider-native. Replace the baseURL and API key only.

cURL
curl https://llm.apixo.ai/v1/responses \
  -H "Authorization: Bearer $APIXO_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "input": "Write a concise product launch brief."
  }'
JavaScript
import OpenAI from 'openai'

const client = new OpenAI({
  apiKey: process.env.APIXO_API_KEY,
  baseURL: 'https://llm.apixo.ai/v1',
})

const response = await client.responses.create({
  model: 'gpt-5.4',
  input: 'Write a concise product launch brief.',
})
Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["APIXO_API_KEY"],
    base_url="https://llm.apixo.ai/v1",
)

response = client.responses.create(
    model="gpt-5.4",
    input="Write a concise product launch brief.",
)

Cursor and compatible tools

Use the same three fields in Cursor, IDE extensions, gateway switchers, or any tool that supports a custom provider endpoint.

Provider profile

OpenAI-compatible

Base URL

https://llm.apixo.ai/v1

API key

APIXO_API_KEY

Model ID

gpt-5.4

Recharge your APIXO balance, then create an API key in the dashboard.

Paste the base URL and API key into the tool's custom provider settings.

Use the selected model ID exactly; switch models by changing only that value.

OpenAI models and pricing

Prices are USD per 1M tokens. Select a row to update the examples above.

ModelInputOutputCache writeCache readSavings
GPT-5.4gpt-5.4$1.375$8.25$0.1375Save 45%
GPT-5.4 Progpt-5.4-pro$16.5$99Save 45%
GPT-5.4 Minigpt-5.4-mini$0.4125$2.475$0.0413Save 45%
GPT-5.4 Nanogpt-5.4-nano$0.11$0.6875$0.011Save 45%
GPT-5.2gpt-5.2$0.9625$7.7$0.0963Save 45%
GPT-5.1gpt-5.1$0.6875$5.5$0.0688Save 45%