AI API keys

Learn how to set up API keys from supported AI providers so you can power your content creation, Content autopilots, and chatbot conversations.

Why you need API keys

WebGPT connects to leading AI providers to generate content, run bots, and power chatbot conversations. Depending on your subscription plan, you may need to supply your own API keys:

Plan type Price range API keys
Independent plans $9 – $149 / month You provide your own API keys from the AI providers you want to use. AI usage costs are billed directly to your provider accounts.
Junior Starter $19 / month AI access is included — the platform provides pre-configured keys so you can start immediately without setting up any provider accounts.
How billing works

When you use your own API keys, all AI costs (token usage, image generation, etc.) are charged directly by the AI provider to the account associated with your key. WebGPT does not add any markup to provider costs.

Supported AI providers

WebGPT supports six major AI providers. You can configure one or more depending on which models you want to use.

OpenAI

OpenAI is the creator of the GPT family of models. It is the most widely used AI provider and offers excellent all-around performance for content creation and reasoning.

  1. Sign in to your OpenAI account (or create one at platform.openai.com).
  2. Navigate to API keys in the left sidebar.
  3. Click Create new secret key, give it a name (e.g., "WebGPT"), and click Create.
  4. Copy the key immediately — OpenAI only shows it once.
  5. Make sure you have billing set up in your OpenAI account under Settings → Billing.

Google Gemini

Google Gemini offers powerful multimodal models with massive context windows. Gemini Flash models are optimized for speed and cost-efficiency.

  1. Sign in with your Google account at Google AI Studio.
  2. Click Get API key in the top navigation.
  3. Click Create API key and select or create a Google Cloud project.
  4. Copy the generated key.

Anthropic Claude

Anthropic Claude models are known for their strong reasoning abilities and excel at long-form content and nuanced analysis. Claude Opus delivers top-tier performance, while Claude Sonnet offers an excellent balance of quality and speed.

  1. Sign in to your Anthropic Console account (or create one at console.anthropic.com).
  2. Navigate to Settings → API keys.
  3. Click Create key, give it a descriptive name, and confirm.
  4. Copy the key — it will not be shown again.
  5. Ensure billing is configured under Settings → Plans & Billing.

DeepSeek

DeepSeek offers high-quality models at a fraction of the cost of other providers. DeepSeek V3.1 is a powerful hybrid model, while DeepSeek R1 specializes in advanced reasoning tasks.

  1. Create an account or sign in at platform.deepseek.com.
  2. Go to API keys in your dashboard.
  3. Click Create new key and copy it.
  4. Add funds to your balance if required.

Grok (xAI)

Grok is developed by xAI and offers models with strong creative, reasoning, and conversational capabilities.

  • Flagship models: Grok 4.1, and more
  • Key format: Starts with xai-
  • Get your key: Visit console.x.ai
  1. Sign in at console.x.ai with your X (Twitter) account.
  2. Navigate to the API keys section.
  3. Generate a new API key and copy it.

Mistral AI

Mistral AI is a French AI company building efficient open-weight and commercial models known for strong multilingual performance and competitive pricing.

  • Flagship models: Mistral Large 3, Mistral Medium, Mistral Small, Pixtral Large, Codestral
  • Key format: No fixed prefix — alphanumeric key of 20+ characters
  • Get your key: Visit console.mistral.ai/api-keys
  1. Sign in or create an account at console.mistral.ai.
  2. Navigate to API keys in your dashboard.
  3. Click Create new key and copy it.
  4. Add funds to your balance if required.

How to add an API key in WebGPT

Once you have your API key from a provider, adding it to WebGPT takes just a few steps:

  1. Navigate to Integrations → AI API keys from the main sidebar menu.
  2. You will see a tab for each supported provider. Click the tab for the provider you want to configure (e.g., OpenAI).
  3. Paste your API key into the key input field.
  4. Click Connect. The system will automatically validate your key by making a test request to the provider.
  5. If the key is valid, a green “Connected” badge will appear and your available models will be displayed with their pricing and capabilities.
  6. If validation fails, double-check that you copied the full key and that your provider account has billing enabled.
Tip

You do not need to configure all providers. Start with one provider (OpenAI is a popular choice) and add others later as needed.

Available models

After connecting a valid API key, your available models are automatically displayed as cards showing their pricing, context window, capabilities, and description. Each provider offers multiple models at different price points:

  • High-performance models (e.g., GPT-5.2, Claude Opus 4.6, Gemini 3 Pro, Mistral Large 3) — best quality output, higher cost per token.
  • Balanced models (e.g., o4-mini, Claude Sonnet 4.5, Gemini 3 Flash, Mistral Medium) — good quality with faster response times and lower costs.
  • Economy models (e.g., DeepSeek V3.1, DeepSeek R1, Mistral Small, Pixtral 12B) — high quality at a fraction of the cost.

Each model card displays:

  • Input and output cost per 1,000 tokens in USD
  • Context window — the maximum number of tokens the model can process in a single request
  • Max output — the maximum number of tokens the model can generate in a response
  • Capability badges — supported modalities such as Text, Vision, Audio, or Code

These models become available for selection throughout the platform — in article creation, bot configuration, and chatbot settings.

Managing your keys

Once a key is connected, you can update or remove it at any time:

  • Update a key: Paste a new key into the input field and click Update. The system will re-validate the key and refresh your model list.
  • Delete a key: Click the delete button next to the key input. After confirmation, the key and all associated model data for that provider will be removed.
Key visibility

For security, stored API keys are partially masked in the interface. Only the first and last few characters are visible. WebGPT never exposes your full key in the browser after it has been saved.

Where API keys are used

Your configured API keys are used across multiple WebGPT features:

  • AI articles — When creating or regenerating content, the selected AI model uses your corresponding provider key.
  • Content autopilots — Scheduled bots that automatically create content use the model and key you configured for the bot.
  • AI chatbots — Conversations with your chatbots use the AI model assigned to each chatbot, powered by your API key.

Tips and best practices

  • Keep your keys secure. Never share your API keys publicly or paste them into untrusted websites. WebGPT stores your keys securely and never exposes them in the browser.
  • Monitor usage on provider dashboards. Each AI provider has its own usage dashboard where you can track spending, set budgets, and configure alerts. Check these regularly to avoid unexpected charges.
  • Set spending limits. Most providers (OpenAI, Anthropic, etc.) allow you to set monthly spending caps. This is a good safety net, especially when running automated bots.
  • Start with one provider, then expand. If you are new to AI APIs, start with a single provider to learn the workflow. You can always add more providers later.
  • Rotate keys periodically. For added security, generate a new key every few months and update it in WebGPT. Delete the old key from the provider dashboard.
  • Use dedicated keys for WebGPT. If you use AI APIs in other applications, consider creating a separate key for WebGPT. This makes it easier to track usage and costs per application.
Important

If your API key expires, is revoked, or runs out of credits, any features that depend on it (articles, bots, chatbots) will stop working until you update the key or add funds to your provider account.

Last updated: April 2026