API Keys (BYOK)

Bring Your Own Key - use your own API keys for unlimited AI chat with full control.

What is BYOK?

BYOK (Bring Your Own Key) allows you to use your own API keys from AI providers instead of Tiny Land's managed models. This gives you:

  • Unlimited Usage: No rate limits from Tiny Land
  • Full Control: Pay only for what you use
  • Cost Transparency: See exactly what you're spending
  • Latest Models: Access new models as soon as they're available
  • Privacy: Direct connection to provider APIs

Managed Models vs BYOK

Managed Models (Default)

  • ✅ Free to use
  • ✅ No setup required
  • ✅ No API key management
  • ⚠️ Rate limits apply
  • ⚠️ Limited model selection

BYOK (Your API Keys)

  • ✅ Unlimited usage
  • ✅ All models available
  • ✅ Full control over costs
  • ✅ Direct API connection
  • ⚠️ Requires API key setup
  • ⚠️ You pay provider directly
💡 Recommendation: Start with managed models to try Tiny Land. Once you're chatting regularly, add your own API keys for unlimited access and lower costs.

Supported Providers

Tiny Land supports API keys from all major AI providers:

OpenAI

  • GPT-5, GPT-5.1, GPT-5 Pro
  • GPT-4.5, GPT-4 Turbo
  • All GPT models

Anthropic (Claude)

  • Claude Opus 4.5, Sonnet 4.5, Haiku 4.5
  • Claude 3.5 family
  • All Claude models

Google

  • Gemini 2.5 Pro, 2.5 Flash
  • Gemini Pro, Gemini Flash
  • All Gemini models

DeepSeek

  • DeepSeek Chat
  • DeepSeek Coder

Others

  • Mistral AI
  • Cohere
  • More providers added regularly

See full list: Available Models

Getting API Keys

OpenAI API Key

  1. Go to platform.openai.com
  2. Sign up or log in
  3. Navigate to API Keys section
  4. Click "Create new secret key"
  5. Copy and save your key (starts with sk-...)
  6. Add billing information

Cost: ~$0.01-0.06 per message depending on model

Anthropic (Claude) API Key

  1. Go to console.anthropic.com
  2. Sign up or log in
  3. Navigate to API Keys
  4. Create a new key
  5. Copy and save your key (starts with sk-ant-...)
  6. Add payment method

Cost: ~$0.01-0.08 per message depending on model

Google (Gemini) API Key

  1. Go to Google AI Studio
  2. Sign in with Google account
  3. Click "Get API Key"
  4. Create a new API key
  5. Copy and save your key

Cost: Free tier available, then ~$0.001-0.02 per message

DeepSeek API Key

  1. Go to platform.deepseek.com
  2. Sign up or log in
  3. Navigate to API section
  4. Create new API key
  5. Copy and save your key

Cost: Very affordable, ~$0.001-0.005 per message

For detailed guides, see: Getting API Keys Guide

Adding API Keys to Tiny Land

Step 1: Access Settings

  1. Click your profile icon
  2. Go to Settings
  3. Click API Keys tab

Step 2: Add Key

  1. Click + Add API Key
  2. Select provider (OpenAI, Anthropic, Google, etc.)
  3. Paste your API key
  4. Give it a nickname (optional, e.g., "My OpenAI Key")
  5. Click Save

Step 3: Verify

  • Tiny Land will test your key
  • If valid, you'll see a success message
  • Invalid keys will show an error message
🔒 Security: Your API keys are encrypted and stored securely. Tiny Land never sees or logs your API key after encryption. Keys are only decrypted temporarily when making API calls.

Using Your API Keys

Selecting Your Key

  1. Start or open a chat
  2. Click Settings (⚙️)
  3. Under "Model", select a model from a provider you have a key for
  4. Your key will automatically be used

Key Indicator

  • 🔑 Icon appears when using your own key
  • Hover to see which key is being used
  • No icon means managed models are being used

Multiple Keys

  • Add multiple keys from the same provider
  • Useful for separating work/personal usage
  • Set a default key per provider
  • Switch between keys anytime

Cost Management

Estimated Costs (Typical Message)

GPT-5: ~$0.03-0.06 per message GPT-4.5: ~$0.01-0.02 per message Claude Opus 4.5: ~$0.04-0.08 per message Claude Sonnet 4.5: ~$0.01-0.03 per message Gemini 2.5 Pro: ~$0.01-0.02 per message Gemini 2.5 Flash: ~$0.001-0.005 per message DeepSeek Chat: ~$0.001-0.003 per message

Costs vary based on message length and context size.

Cost-Saving Tips

  • Use cheaper models for casual chats (Gemini Flash, DeepSeek)
  • Reserve expensive models (GPT-5, Opus 4.5) for important conversations
  • Reduce context length in settings to use fewer tokens
  • Use managed models when you don't need unlimited access

Usage Tracking

  • View usage stats in API Keys settings
  • See total tokens used per key
  • Estimated cost breakdown
  • Check provider dashboards for exact billing

Managing API Keys

Editing Keys

  • Edit nickname or description
  • Set as default for provider
  • Update key if it changes

Deleting Keys

  • Remove keys you no longer use
  • Existing chats will fall back to managed models
  • Delete keys immediately if compromised

Key Security

  • Never share your API keys
  • Rotate keys periodically
  • Set spending limits on provider dashboards
  • Monitor usage for unexpected activity
  • Delete keys if you suspect they're compromised

Troubleshooting

Key Not Working

  • Verify key is correct (no extra spaces)
  • Check if key is active on provider dashboard
  • Ensure billing is set up with provider
  • Verify provider account has available credits

Rate Limit Errors

  • Some providers have rate limits even with API keys
  • Wait a moment and try again
  • Consider upgrading your provider account tier

High Costs

  • Check context length settings (lower = cheaper)
  • Use less expensive models for casual chats
  • Review provider dashboard for unusual activity
  • Set spending limits on provider dashboards
💡 Pro Tip: Add keys from multiple providers to try different models. Claude excels at creative roleplay, GPT-5 is great for complex conversations, and Gemini Flash is perfect for long chats on a budget.
Detailed API Key Guides →Available Models →Choosing the Right Model →