Multimodal inputs

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key=os.environ["NAGAAI_API_KEY"])

response = client.responses.create(
    model="deepseek-v4.1-flash",
    input=[{
        "role": "user",
        "content": [
            {"type": "input_text", "text": "What is in this image? One sentence."},
            {"type": "input_image", "image_url": "https://media.naga.ac/outputs/6ab3444c-f19e-4944-80dc-d0b49c49c144.png"},
        ],
    }],
)

print(response.output_text)

import OpenAI from "openai";

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

const response = await client.responses.create({
  model: "deepseek-v4.1-flash",
  input: [{
    role: "user",
    content: [
      { type: "input_text", text: "What is in this image? One sentence." },
      { type: "input_image", image_url: "https://media.naga.ac/outputs/6ab3444c-f19e-4944-80dc-d0b49c49c144.png" },
    ],
  }],
});

console.log(response.output_text);