Code Examples

Use the official openai package. Just pass the CheapAI base URL — everything else stays the same.

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ.get("CHEAPAI_API_KEY"),
    base_url="https://cheapai-netifly-app.up.railway.app/v1",
)

# Call Claude 4.6 Sonnet via the OpenAI SDK wrapper
response = client.chat.completions.create(
    model="claude-sonnet-4-6-20260217",
    messages=[{"role": "user", "content": "What is 17 * 43?"}],
)
print(response.choices[0].message.content)

The official npm openai package, with streaming enabled and the Gemini 3.1 Pro Preview model.

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.CHEAPAI_API_KEY,
  baseURL: 'https://cheapai-netifly-app.up.railway.app/v1',
});

async function main() {
  const stream = await client.chat.completions.create({
    model: 'gemini-3.1-pro-preview',
    messages: [{ role: 'user', content: 'Explain HTTP streaming.' }],
    stream: true,
  });

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

Override base_url on the ChatOpenAI wrapper. The rest of the LCEL toolchain works natively.

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
import os

llm = ChatOpenAI(
    api_key=os.environ.get("CHEAPAI_API_KEY"),
    base_url="https://cheapai-netifly-app.up.railway.app/v1",
    model="claude-sonnet-4-6-20260217",
)

prompt = ChatPromptTemplate.from_messages([
    ("system", "Translate to {target_language}."),
    ("user", "{text}")
])

chain = prompt | llm | StrOutputParser()
print(chain.invoke({"target_language": "French", "text": "Hello, world!"}))

For raw terminal access or debugging API payloads. Works with DeepSeek, Claude, and Gemini model IDs.

curl https://cheapai-netifly-app.up.railway.app/v1/chat/completions \
  -H "Authorization: Bearer $CHEAPAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-chat",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Set these environment variables to route all OpenAI-type requests through CheapAI. The /v1/models endpoint returns a full model list, so available models appear automatically in the UI dropdown.

OPENAI_API_BASE_URL=https://cheapai-netifly-app.up.railway.app/v1
OPENAI_API_KEY=your_cheapai_key