SDK examples

Call the API with curl, fetch, the OpenAI Python and Node SDKs and the Anthropic SDKs by overriding the base URL.

You do not need a special client. Point an official SDK at the base URL, give it your key, and use a model id from GET /v1/models. The examples read the key from the AIP_API_KEY environment variable.

curl

bash

curl -sS https://api.ticonai.com/v1/chat/completions \
  -H "Authorization: Bearer $AIP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "your-model-id",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "max_tokens": 64
  }'

fetch (Node 18 and later, or any runtime with fetch)

const res = await fetch("https://api.ticonai.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIP_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "your-model-id",
    messages: [{ role: "user", content: "Hello!" }],
    max_tokens: 64,
  }),
});
if (!res.ok) throw new Error(`HTTP ${res.status}`);
console.log(JSON.stringify(await res.json()));

OpenAI SDK for Python

Install with pip install openai. Set base_url to the base URL, which ends in /v1.

python

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.ticonai.com/v1",
    api_key=os.environ["AIP_API_KEY"],
)

response = client.chat.completions.create(
    model="your-model-id",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=64,
)
print(response.choices[0].message.content)

Streaming with the same client:

python

stream = client.chat.completions.create(
    model="your-model-id",
    messages=[{"role": "user", "content": "Count to five."}],
    max_tokens=64,
    stream=True,
    stream_options={"include_usage": True},
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

OpenAI SDK for Node.js

Install with npm install openai.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.ticonai.com/v1",
  apiKey: process.env.AIP_API_KEY,
});

const response = await client.chat.completions.create({
  model: "your-model-id",
  messages: [{ role: "user", content: "Hello!" }],
  max_tokens: 64,
});
console.log(response.choices[0].message.content);

Anthropic SDK for Python

Install with pip install anthropic. The Anthropic SDK adds /v1/messages itself, so set base_url to the origin without /v1.

python

import os
import anthropic

client = anthropic.Anthropic(
    base_url="https://api.ticonai.com",
    api_key=os.environ["AIP_API_KEY"],
)

message = client.messages.create(
    model="your-model-id",
    max_tokens=64,
    messages=[{"role": "user", "content": "Hello!"}],
)
print(message.content[0].text)

Anthropic SDK for Node.js

Install with npm install @anthropic-ai/sdk.

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  baseURL: "https://api.ticonai.com",
  apiKey: process.env.AIP_API_KEY,
});

const message = await client.messages.create({
  model: "your-model-id",
  max_tokens: 64,
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(message.content[0].type === "text" ? message.content[0].text : "");

Notes

The key is accepted as Authorization: Bearer and as x-api-key, which is what the OpenAI and Anthropic SDKs send by default.
SDK retries are fine for 429 and 5xx. For non-streaming calls, also send an Idempotency-Key header so a retry cannot bill twice: both SDKs let you add default or per-request headers. See Idempotency.
Errors raised by the SDKs wrap the HTTP status and body described in Errors.