More APIs

DEVUP Native API

Advanced API with access to all model types including image generation, speech, object detection, and more.

The DEVUP Native API gives you access to every model we provide, including model types not covered by the OpenAI-compatible API: image generation, speech recognition, object detection, token classification, fill mask, image classification, zero-shot image classification, and text classification.

For LLMs and embeddings, the OpenAI-compatible API is simpler and recommended. Use the native API when you need model types beyond LLMs/embeddings, or when you need features like webhooks or log probabilities.

bash

https://api.devupai.com/v1/chat/completions

JavaScript client

bash

npm install devupai

Text Generation (LLMs)

// For LLMs, use the OpenAI-compatible API instead:
const response = await fetch("https://api.devupai.com/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": \`Bearer \${DEVUP_API_KEY}\`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "deepseek-ai/DeepSeek-V4-Pro",
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
const data = await response.json();
console.log(data.choices[0].message.content);

Embeddings

const response = await fetch("https://api.devupai.com/v1/embeddings", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": `Bearer $DEVUP_API_KEY`
  },
  body: JSON.stringify({
    model: "Qwen/Qwen3-Embedding-8B",
    input: [
      "What is the capital of France?",
      "What is the capital of Germany?"
    ]
  })
});

const output = await response.json();
console.log(output.data[0].embedding);

Image Generation

import { createWriteStream } from "fs";
import { Readable } from "stream";

const response = await fetch("https://api.devupai.com/v1/images/generations", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": `Bearer $DEVUP_API_KEY`
  },
  body: JSON.stringify({
    model: "stabilityai/stable-diffusion-2-1",
    prompt: "a burger with a funny hat on the beach"
  })
});

const output = await response.json();
const result = await fetch(output.data[0].url);
if (result.ok && result.body) {
  Readable.fromWeb(result.body).pipe(createWriteStream("image.png"));
}

Speech Recognition

bash

curl -X POST \
  -H "Authorization: Bearer $DEVUP_API_KEY" \
  -F "model=openai/whisper-large-v3" \
  -F "file=@audio.mp3" \
  'https://api.devupai.com/v1/audio/speech'

Object Detection

bash

curl -X POST \
  -H "Authorization: Bearer $DEVUP_API_KEY" \
  -F "model=hustvl/yolos-small" \
  -F "image=@image.jpg" \
  'https://api.devupai.com/v1/chat/completions'

Token Classification

bash

curl -X POST \
  -d '{"model": "Davlan/bert-base-multilingual-cased-ner", "input": "My name is John Doe and I live in San Francisco."}' \
  -H "Authorization: Bearer $DEVUP_API_KEY" \
  -H "Content-Type: application/json" \
  'https://api.devupai.com/v1/chat/completions'

Fill Mask

bash

curl -X POST \
  -d '{"model": "bert-base-cased", "input": "I need my [MASK] right now!"}' \
  -H "Authorization: Bearer $DEVUP_API_KEY" \
  -H "Content-Type: application/json" \
  'https://api.devupai.com/v1/chat/completions'

Image Classification

bash

curl -X POST \
  -H "Authorization: Bearer $DEVUP_API_KEY" \
  -F "model=google/vit-base-patch16-224" \
  -F "image=@image.jpg" \
  'https://api.devupai.com/v1/chat/completions'

Zero-Shot Image Classification

bash

curl -X POST \
  -H "Authorization: Bearer $DEVUP_API_KEY" \
  -F "model=openai/clip-vit-base-patch32" \
  -F "image=@image.jpg" \
  -F 'candidate_labels=["dog", "cat", "car", "horse", "person"]' \
  'https://api.devupai.com/v1/chat/completions'

Text Classification

bash

curl -X POST \
  -d '{"model": "ProsusAI/finbert", "input": "Nvidia announces new AI chips months after latest launch"}' \
  -H "Authorization: Bearer $DEVUP_API_KEY" \
  -H 'Content-Type: application/json' \
  'https://api.devupai.com/v1/chat/completions'

HTTP / other languages

The native API is plain HTTP — you can use it from any language (Go, C#, Java, PHP, Ruby, C++, etc.) without any SDK dependency.

Text to Speech