Code Examples

Ready-to-run samples in Python, JavaScript, and curl.

Switch from OpenAI in 3 small edits — base URL, API key, and the model id (tier-1 … tier-4). Text chat completions only; tool calling isn't supported yet.

Python (OpenAI SDK)

Use the official OpenAI Python client pointed at the TierUp.AI base URL.

python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.tierup.ai/v1",  # ← Changed
    api_key="tup_your_api_key_here",       # ← Changed
)

response = client.chat.completions.create(
    model="tier-2",  # ← Changed — pick tier-1 … tier-4
    messages=[{"role": "user", "content": "Explain quantum computing"}],
)

print(response.choices[0].message.content)

Python with Streaming

Enable streaming to receive tokens as they are generated.

python

stream = client.chat.completions.create(
    model="tier-1",
    messages=[{"role": "user", "content": "Write a poem"}],
    stream=True,
)

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

JavaScript (fetch)

Works in any environment that supports the Fetch API — browsers, Node.js, Deno, and edge runtimes.

javascript

const response = await fetch("https://api.tierup.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer tup_your_api_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    messages: [{ role: "user", content: "Hello!" }],
    tier: 1,
  }),
});

const data = await response.json();
console.log(data.choices[0].message.content);

JavaScript with Streaming

Read the response body as a stream and parse each server-sent event line.

javascript

const response = await fetch("https://api.tierup.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer tup_your_api_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    messages: [{ role: "user", content: "Hello!" }],
    tier: 2,
    stream: true,
  }),
});

const reader = response.body.getReader();
const decoder = new TextDecoder();

while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  const chunk = decoder.decode(value);
  for (const line of chunk.split("\n")) {
    if (line.startsWith("data: ") && line !== "data: [DONE]") {
      const data = JSON.parse(line.slice(6));
      process.stdout.write(data.choices?.[0]?.delta?.content || "");
    }
  }
}

curl

The quickest way to test from a terminal without any dependencies.

bash

curl -X POST https://api.tierup.ai/v1/chat/completions \
  -H "Authorization: Bearer tup_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{"messages": [{"role": "user", "content": "Hello!"}], "tier": 1}'

curl with Streaming

Pass -N to disable curl's output buffering so you see tokens as they arrive.

bash

curl -N -X POST https://api.tierup.ai/v1/chat/completions \
  -H "Authorization: Bearer tup_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{"messages": [{"role": "user", "content": "Hello!"}], "tier": 2, "stream": true}'

Install the OpenAI SDK

Python:

bash

pip install openai

Node.js:

bash

npm install openai