API Code Examples

Our API is designed for simplicity and is fully compatible with the OpenAI SDK. To switch your existing project to NagaAI, you only need to change the base_url and api_key.

• Base URL: https://api.naga.ac/v1
• API Key: Your unique key from the NagaAI Dashboard.

View Rate Limits

You can check the specific rate limits for all models at any time by visiting: api.naga.ac/v1/limits

Client Initialization

First, set up the client in your preferred language.

Python

from openai import OpenAI

client = OpenAI(
    base_url='https://api.naga.ac/v1',
    api_key='YOUR_API_KEY'
)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.naga.ac/v1",
  apiKey: "YOUR_API_KEY",
});

Core Endpoints

Below are practical, copy-paste examples for the most common API endpoints.

Chat Completions

Generate text-based responses for conversations or content creation.

Python

response = client.chat.completions.create(
    model='gpt-4o-mini',
    messages=[{'role': 'user', 'content': "What's 2+2?"}]
)
print(response.choices[0].message.content)

Node.js

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "What's 2+2?" }],
});
console.log(response.choices[0].message.content);

cURL

curl https://api.naga.ac/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "What'\''s 2+2?"
      }
    ]
  }'

Image Generation

Create an image from a text prompt.

Python

response = client.images.generate(
    model='flux-1-schnell',
    prompt='A white siamese cat'
)
print(response.data)

Node.js

const response = await client.images.generate({
  model: "flux-1-schnell",
  prompt: "A white siamese cat",
});
console.log(response.data);

cURL

curl https://api.naga.ac/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-1-schnell",
    "prompt": "A white siamese cat"
  }'

Text-to-Speech (TTS)

Convert text into spoken audio.

Python

from pathlib import Path

speech_file_path = Path(__file__).parent / "speech.mp3"
response = client.audio.speech.create(
    model='gpt-4o-mini-tts',
    voice='alloy',  # type: ignore
    input='Hello and welcome to the NagaAI!'
)
response.stream_to_file(speech_file_path)

Node.js

import fs from "fs";
import path from "path";

const speechFile = path.resolve("./speech.mp3");

const mp3 = await client.audio.speech.create({
  model: "gpt-4o-mini-tts",
  voice: "alloy",
  input: "Hello and welcome to the NagaAI!",
});

const buffer = Buffer.from(await mp3.arrayBuffer());
await fs.promises.writeFile(speechFile, buffer);

cURL

curl https://api.naga.ac/v1/audio/speech \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini-tts",
    "voice": "alloy",
    "input": "Hello and welcome to the NagaAI!"
  }' \
  --output speech.mp3

Speech-to-Text (STT)

Transcribe an audio file into text.

Python

audio_file = open('/path/to/file/audio.mp3', 'rb')
transcription = client.audio.transcriptions.create(
  model='gpt-4o-transcribe',
  file=audio_file
)
print(transcription.text)

Node.js

import fs from "fs";

const transcription = await client.audio.transcriptions.create({
  file: fs.createReadStream("/path/to/file/audio.mp3"),
  model: "gpt-4o-transcribe",
});

console.log(transcription.text);

cURL

curl https://api.naga.ac/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@/path/to/file/audio.mp3" \
  -F model="gpt-4o-transcribe"

Translations

Translate an audio file into English.

Python

audio_file = open('/path/to/file/german.mp3', 'rb')
translation = client.audio.translations.create(
    model='whisper-large-v3',
    file=audio_file
)
print(translation.text)

Node.js

import fs from "fs";

const translation = await client.audio.translations.create({
  file: fs.createReadStream("/path/to/file/german.mp3"),
  model: "whisper-large-v3",
});

console.log(translation.text);

cURL

curl https://api.naga.ac/v1/audio/translations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@/path/to/file/german.mp3" \
  -F model="whisper-large-v3"

Image Edits

Edit an existing image based on a prompt.

Python

response = client.images.edit(
    model='gpt-image-1',
    image=[open("image_1.png", "rb"), open("image_2.png", "rb")],
    prompt='Make the clouds in image 1 look like the ones in image 2'
)
print(response.data)

Node.js

import fs from "fs";

const response = await client.images.edit({
  model: "gpt-image-1",
  image: fs.createReadStream("image_1.png"),
  prompt: "Make the clouds in image 1 look like the ones in image 2",
});
console.log(response.data);

cURL

curl https://api.naga.ac/v1/images/edits \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F image="@image_1.png" \
  -F prompt="Make the clouds in image 1 look like the ones in image 2" \
  -F model="gpt-image-1"

Embeddings

Generate vector embeddings for a piece of text.

Python

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="The food was delicious!",
)
print(response)

Node.js

const response = await client.embeddings.create({
  model: "text-embedding-3-small",
  input: "The food was delicious!",
});
console.log(response);

cURL

curl https://api.naga.ac/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "The food was delicious!"
  }'

Moderations

Check if a text string violates OpenAI's usage policies.

Python

response = client.moderations.create(model='omni-moderation-latest', input='Hello! Nice to meet you!')
print(response.results[0])

Node.js

const response = await client.moderations.create({
  model: "omni-moderation-latest",
  input: "Hello! Nice to meet you!",
});
console.log(response.results[0]);

cURL

curl https://api.naga.ac/v1/moderations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "omni-moderation-latest",
    "input": "Hello! Nice to meet you!"
  }'