Earbowe API Quickstart

Updated 2026-07-24 · Technical setup guide.

Get a key, set the base URL, make one successful request.

Base URLs

Always include the /v1 suffix for OpenAI-compatible clients.

1. Create a key

1. Open Console
2. Sign in / sign up
3. Create a token (sk-...)

2. List models

curl -sS https://api.earbowe.com/v1/models \
  -H "Authorization: Bearer sk-..."

Use only model IDs returned for your token.

3. Chat completion (curl)

curl -sS https://api.earbowe.com/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [{"role":"user","content":"Say hello in one short sentence."}]
  }'

4. Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="sk-...",
    base_url="https://api.earbowe.com/v1",
)

resp = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "ping"}],
)
print(resp.choices[0].message.content)

5. Node.js (OpenAI SDK)

import OpenAI from "openai";

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

const resp = await client.chat.completions.create({
  model: "gpt-5.5",
  messages: [{ role: "user", content: "ping" }],
});
console.log(resp.choices[0].message.content);

Common mistakes

• Using https://www.earbowe.com as API base — wrong. Use api.earbowe.com.
• Forgetting /v1.
• Copying model names from marketing pages instead of /v1/models.
• In China, sticking to the global host when the direct host is faster: api.3861343.xyz.

Next: Models · Codex guide · All guides