JavaScript examples

Chat completions

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://llm.aihosting.mittwald.de/v1" });

const resp = await client.chat.completions.create({
  model: "Devstral-Small-2-24B-Instruct-2512",
  messages: [{ role: "user", content: "Hello from JS!" }],
});

console.log(resp.choices[0].message.content);

Vision (image + text)

Vision models on mittwald AI Hosting accept images as Base64-encoded data URLs only. Sending image URLs is not supported and results in a server error.

Note

If you use a tool such as Open WebUI or LibreChat, image uploads are handled automatically - these tools encode and resize images transparently before sending them to the API. The Base64 encoding below is only required when calling the API directly from code.

Encoding and resizing images

Install sharp for image processing:

npm install sharp

Always resize before encoding. Sending large images significantly increases time to first token (TTFT). Keeping the longest edge at 1024 px or below is a safe default that preserves quality for most tasks:

import sharp from "sharp";

async function encodeImage(path: string, maxPx = 1024): Promise<string> {
  const img = sharp(path);
  const { width = 0, height = 0 } = await img.metadata();
  const longest = Math.max(width, height);
  const resized =
    longest > maxPx
      ? img.resize(width >= height ? maxPx : undefined, height > width ? maxPx : undefined)
      : img;
  const buf = await resized.jpeg({ quality: 85 }).toBuffer();
  return `data:image/jpeg;base64,${buf.toString("base64")}`;
}

Making a vision request

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://llm.aihosting.mittwald.de/v1" });

const resp = await client.chat.completions.create({
  model: "Ministral-3-14B-Instruct-2512",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Describe this image in detail." },
        { type: "image_url", image_url: { url: await encodeImage("photo.jpg") } },
      ],
    },
  ],
  temperature: 0.1,
  max_tokens: 512,
});

console.log(resp.choices[0].message.content);

Choosing a vision model

Model	Max images	Strengths
Qwen3.5-122B-A10B-FP8	20+	Best accuracy, OCR, complex scenes
Ministral-3-14B-Instruct-2512	4	Balanced speed and quality
Qwen3.6-35B-A3B-FP8	5+	Fast on warm requests
Devstral-Small-2-24B-Instruct-2512	4	Code-heavy workflows with images

For Qwen models, disable thinking mode in vision requests to avoid unnecessary overhead:

const resp = await client.chat.completions.create({
  model: "Qwen3.5-122B-A10B-FP8",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Extract all text from this document." },
        { type: "image_url", image_url: { url: await encodeImage("document.jpg") } },
      ],
    },
  ],
  temperature: 0.7,
  max_tokens: 1024,
  // @ts-expect-error vLLM-specific parameter not in OpenAI types
  extra_body: { chat_template_kwargs: { enable_thinking: false } },
});

console.log(resp.choices[0].message.content);

Tool calling (function calling)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://llm.aihosting.mittwald.de/v1" });

const tools = [
  {
    type: "function",
    function: {
      name: "get_weather",
      description: "Get current weather for a city",
      parameters: {
        type: "object",
        properties: {
          city: { type: "string", description: "City name" },
        },
        required: ["city"],
      },
    },
  },
];

const resp = await client.chat.completions.create({
  model: "Devstral-Small-2-24B-Instruct-2512",
  messages: [{ role: "user", content: "What is the weather in Munich?" }],
  tools,
  tool_choice: "auto",
});

const toolCall = resp.choices[0].message.tool_calls?.[0];
if (toolCall) {
  console.log(`Function: ${toolCall.function.name}`);
  console.log(`Arguments: ${toolCall.function.arguments}`);
}

Streaming responses

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://llm.aihosting.mittwald.de/v1" });

const stream = await client.chat.completions.create({
  model: "Devstral-Small-2-24B-Instruct-2512",
  messages: [{ role: "user", content: "Write a short poem about coding" }],
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content || "";
  process.stdout.write(content);
}