OpenAI GPT-3 API error 429: "Request failed with status code 429"

As stated in the official OpenAI article:

This (i.e., 429) error message indicates that you have hit your assigned rate limit for the API. This means that you have submitted too many tokens or requests in a short period of time and have exceeded the number of requests allowed. This could happen for several reasons, such as:

• You are using a loop or a script that makes frequent or concurrent requests.

• You are sharing your API key with other users or applications.

• You are using a free plan that has a low rate limit.

Working example

Frontend

HelloWorld.vue

<template>
  <div class="hello"></div>

  <select v-model="selected" @change="handleSelect()">
    <option disabled value="">Please select one</option>
    <option>Say this is a test</option>
    <option>Say nothing</option>
  </select>

  <div class="container-selected">Selected: {{ selected }}</div>

  <div class="container-data" v-if="showData">{{ showData.bot }}</div>
</template>

<script>
export default {
  data: function () {
    return {
      selected: "",
      showData: "",
    };
  },
  methods: {
    async handleSelect(data) {
      try {
        const res = await fetch("http://localhost:3000/", {
          method: "POST",
          headers: {
            "Content-Type": "application/json",
          },
          body: JSON.stringify({
            question: this.selected,
          }),
        });

        const data = await res.json();
        this.showData = data;
        console.log(data);
      } catch {
        console.log(data);
      }
    },
  },
};
</script>

<style lang="scss">
.container-selected {
  margin-top: 12px;
  font-size: 20px;
}

.container-data {
  margin-top: 24px;
  font-size: 20px;
}
</style>

package.json

{
  "name": "openai",
  "version": "0.1.0",
  "private": true,
  "scripts": {
    "serve": "vue-cli-service serve",
    "build": "vue-cli-service build",
    "lint": "vue-cli-service lint"
  },
  "dependencies": {
    "register-service-worker": "^1.7.2",
    "vue": "^3.2.13",
    "vue-class-component": "^8.0.0-0",
    "vue-router": "^4.0.3",
    "vuex": "^4.0.0"
  },
  "devDependencies": {
    "@typescript-eslint/eslint-plugin": "^5.4.0",
    "@typescript-eslint/parser": "^5.4.0",
    "@vue/cli-plugin-eslint": "~5.0.0",
    "@vue/cli-plugin-pwa": "~5.0.0",
    "@vue/cli-plugin-router": "~5.0.0",
    "@vue/cli-plugin-typescript": "~5.0.0",
    "@vue/cli-plugin-vuex": "~5.0.0",
    "@vue/cli-service": "~5.0.0",
    "@vue/eslint-config-typescript": "^9.1.0",
    "eslint": "^7.32.0",
    "eslint-config-prettier": "^8.3.0",
    "eslint-plugin-prettier": "^4.0.0",
    "eslint-plugin-vue": "^8.0.3",
    "prettier": "^2.4.1",
    "sass": "^1.32.7",
    "sass-loader": "^12.0.0",
    "typescript": "~4.5.5"
  }
}

Backend

index.js

const express = require('express');
const app = express();
app.use(express.json());

const cors = require('cors');
app.use(cors());

app.post('/', async(req, res) => {
  try {
    const { Configuration, OpenAIApi } = require('openai');
    const configuration = new Configuration({
        apiKey: 'sk-xxxxxxxxxxxxxxxxxxxx'
    });
    const openai = new OpenAIApi(configuration);

    const question = req.body.question;

    await openai.createCompletion({
      model: 'text-davinci-003',
      prompt: question,
      temperature: 0,
      max_tokens: 7
    })
    .then((response) => {
      console.log(response.data.choices[0].text);
      res.status(200).send({ bot: response.data.choices[0].text });
    })
    .catch((err) => {
      res.status(400).send({ message: err.message });
    })
  } catch (error) {
    res.status(500).send(error || 'Something went wrong');
  }
});

const PORT = process.env.PORT || 3000;
app.listen(PORT, () => {
  console.log(`Server is running on port ${PORT}.`);
});

package.json

{
  "name": "openai-server",
  "version": "1.0.0",
  "description": "Express server",
  "main": "index.js",
  "scripts": {
    "test": "echo \"Error: no test specified\" && exit 1"
  },
  "author": "",
  "license": "ISC",
  "dependencies": {
    "cors": "^2.8.5",
    "express": "^4.18.2",
    "nodemon": "^2.0.20",
    "openai": "^3.1.0"
  }
}

Output

Solution: add credit.

1. Go to account settings: https://platform.openai.com/settings
2. Click 'Billing'
3. Click on 'Add credit to balance'
4. Wait 2-3 minutes for it to take effect.

More info here.

I'm not sure why the OpenAI API throws a 429 Too many requests when you don't have sufficient credit on your OpenAI API account, that's a bit confusing as those two things seem unrelated.