Quickstart
Get started in 5 minutes
Three steps: get an API key, install the SDK, make your first call. Everything else is optional.
Step 1 — Get your API key
Create a free account at belugapi.com.
Once registered, navigate to Dashboard → API Keys → New Key.
Your key looks like bapi_xxxxxxxxxxxxx.
Keep it secret. Never commit your API key to git or expose it in client-side JavaScript. Use environment variables.
Store it as an env variable
export BELUGAPI_KEY="bapi_your_key_here"
BELUGAPI_KEY=bapi_your_key_here
Step 2 — Install the SDK
BelugAPI is OpenAI-compatible. Install the official OpenAI SDK for your language.
pip install openai
npm install openai
# No installation needed — use curl or any HTTP client
Step 3 — Your first chat call
Point the SDK at https://api.belugapi.com/v1 — that's the only change you need.
import os from openai import OpenAI client = OpenAI( api_key=os.getenv("BELUGAPI_KEY"), base_url="https://api.belugapi.com/v1", ) response = client.chat.completions.create( model="gpt-5.4", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is BelugAPI?"}, ], ) print(response.choices[0].message.content) # Usage info print(response.usage.total_tokens, "tokens")
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.BELUGAPI_KEY, baseURL: "https://api.belugapi.com/v1", }); const res = await client.chat.completions.create({ model: "gpt-5.4", messages: [ { role: "system", content: "You are a helpful assistant." }, { role: "user", content: "What is BelugAPI?" }, ], }); console.log(res.choices[0].message.content); console.log(res.usage?.total_tokens, "tokens");
curl https://api.belugapi.com/v1/chat/completions \ -H "Authorization: Bearer $BELUGAPI_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-5.4", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is BelugAPI?"} ] }'
Streaming responses
Add "stream": true to receive tokens as Server-Sent Events (SSE) — same as OpenAI.
with client.chat.completions.stream( model="gpt-5.4", messages=[{"role": "user", "content": "Tell me a short story."}], ) as stream: for chunk in stream.text_stream: print(chunk, end="", flush=True)
const stream = await client.chat.completions.stream({ model: "gpt-5.4", messages: [{ role: "user", content: "Tell me a short story." }], }); for await (const chunk of stream) { process.stdout.write(chunk.choices[0]?.delta?.content ?? ""); }
Next steps
- Browse the model catalog — 200+ models available
- Chat Completions reference — all parameters explained
- Image generation — GPT-Image-2, Seedream, and more
- Video generation — Sora 2, Veo 3, Kling, and more
- Audio — TTS & STT — text-to-speech and transcription
- Error codes & rate limits