Imference API – Documentation

Reference for the public endpoints used to generate and retrieve images

Looking for the pricing & quick start page? Go to the main page →

Pay-per-use API

You can test the pay-per-use on our main page

To integrate in your app you can use the quick start guide for buyers from the x402 documentation

Endpoints

POST /ondemand/generate GET /ondemand/status

POST /ondemand/generate

Generate an on-chain payment and queue a new image generation for a given model and text description.

curl -X POST \
  'https://imference.com/ondemand/generate' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "illustrious-hassuka-xl",
    "prompt": "A cat astronaut floating in space",
    "wallet_address": "0x123"
  }'

package main

import (
  "bytes"
  "encoding/json"
  "fmt"
  "io"
  "net/http"
)

func main() {
  body := map[string]string{
    "model": "illustrious-hassuka-xl",
    "prompt": "A cat astronaut floating in space",
    "wallet_address": "0x123",
  }

  payload, _ := json.Marshal(body)

  req, err := http.NewRequest(
      "POST",
      "https://imference.com/ondemand/generate",
      bytes.NewReader(payload),
    )
  if err != nil {
    panic(err)
  }

  req.Header.Set("Content-Type", "application/json")

  res, err := http.DefaultClient.Do(req)
  if err != nil {
    panic(err)
  }
  defer res.Body.Close()

  b, _ := io.ReadAll(res.Body)
  fmt.Println(string(b))
}

import requests

url = "https://imference.com/ondemand/generate"
headers = {
    "Content-Type": "application/json",
}
json_data = {
    "model": "illustrious-hassuka-xl",
    "prompt": "A cat astronaut floating in space",
    "wallet_address":"0x123",
}

response = requests.post(url, headers=headers, json=json_data)
print(response.status_code, response.json())

const payload = {
  model: "illustrious-hassuka-xl",
  prompt: "A cat astronaut floating in space",
  wallet_address:"0x123",
};

fetch("https://imference.com/ondemand/generate", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
  },
  body: JSON.stringify(payload),
})
  .then((res) => res.json())
  .then((data) => console.log("request_id:", data.request_id))
  .catch(console.error);

interface GeneratePayload {
  model: string;
  prompt: string;
  wallet_address: string;
}

async function generateImage() {
  const payload: GeneratePayload = {
    model: "illustrious-hassuka-xl",
    prompt: "A cat astronaut floating in space",
    wallet_address: "0x123",
  };

  const res = await fetch("https://imference.com/ondemand/generate", {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
    },
    body: JSON.stringify(payload),
  });

  const data = await res.json();
  console.log("request_id:", data.request_id);
}

generateImage().catch(console.error);

GET /ondemand/status

Look up the status of an image generation by its request_id.

curl -X GET \
  'https://imference.com/ondemand/status?request_id=<REQUEST_ID>'

package main

import (
  "fmt"
  "io"
  "net/http"
)

func main() {
  requestID := "<REQUEST_ID>"
  url := "https://imference.com/ondemand/status?request_id=" + requestID

  req, _ := http.NewRequest("GET", url, nil)

  res, err := http.DefaultClient.Do(req)
  if err != nil {
    panic(err)
  }
  defer res.Body.Close()

  body, _ := io.ReadAll(res.Body)
  fmt.Println(string(body))
}

import requests

request_id = "<REQUEST_ID>"
url = f"https://imference.com/ondemand/status?request_id={request_id}"

response = requests.get(url)
print(response.status_code, response.json())

const requestId = "<REQUEST_ID>";

fetch(`https://imference.com/ondemand/status?request_id=${requestId}`, {
  method: "GET",
})
  .then((res) => res.json())
  .then((data) => console.log(data))
  .catch(console.error);

const requestId: string = "<REQUEST_ID>";

async function getStatus() {
  const res = await fetch(
    `https://imference.com/ondemand/status?request_id=${requestId}`,
    {
      method: "GET",
    },
  );

  const data = await res.json();
  console.log(data);
}

getStatus().catch(console.error);