Account & Security

Webhooks

Receive inference results asynchronously via HTTP callbacks.

Webhooks are a feature of the DEVUP Native API. They are not supported with the OpenAI-compatible API. Webhooks let you submit an inference request and receive the result via an HTTP callback, instead of waiting for the response synchronously. This is useful for long-running requests or fire-and-forget workloads.

How it works

Add a webhook parameter to your request. The API immediately responds with status queued, then calls your webhook URL with the result once inference is complete.

Text generation example

import { TextGeneration } from "devupai";

const client = new TextGeneration(
  "https://api.devupai.com/v1/inference/deepseek-ai/DeepSeek-V3",
  "$DEVUP_API_KEY"
);

const res = await client.generate({
  input: "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nHello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
  stop: ["<|eot_id|>"],
  webhook: "https://your-app.com/devupai-webhook"
});

console.log(res.inference_status.status); // "queued"

Embeddings example

bash

curl "https://api.devupai.com/v1/inference/Qwen/Qwen3-Embedding-8B" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DEVUP_API_KEY" \
  -d '{
    "inputs": ["I like chocolate"],
    "webhook": "https://your-app.com/devupai-webhook"
  }'

Webhook payload

On success, your endpoint receives:

json

{
  "request_id": "R7X9fdLIaF56lVisBAi5xR3E",
  "inference_status": {
    "status": "succeeded",
    "runtime_ms": 228,
    "cost": 0.0001140000022132881
  },
  "results": { ... }
}

On failure:

json

{
  "request_id": "RHNShFanUP5ExA8rzgyDWH88",
  "inference_status": {
    "status": "failed",
    "runtime_ms": 0,
    "cost": 0.0
  }
}

Retry behavior

DEVUP AI will make a few retry attempts if your webhook endpoint returns a 4xx or 5xx status code.

Rate Limits