API Documentation

⚡ Quick Start

Botstrapp.ai is fully OpenAI-compatible. Use any OpenAI SDK — just change the base URL and API key.

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://botstrapp.ai/v1",
    api_key="bst_your_api_key_here",
)

response = client.chat.completions.create(
    model="gemini/gemini-2.5-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

JavaScript / Node.js

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: 'https://botstrapp.ai/v1',
    apiKey: 'bst_your_api_key_here',
});

const response = await client.chat.completions.create({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0].message.content);

cURL

curl https://botstrapp.ai/v1/chat/completions \
  -H "Authorization: Bearer bst_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

🤖 Available Models

Access models from 10+ providers through a single API. Use GET /v1/catalog for the live list.

How billing works

These are estimates, not fixed prices. When you send a message, the estimate is held from your balance. After the response completes, the charge settles to the actual provider cost × 1.35 platform markup (the rate is public — see the X-Botstrapp-Markup-Rate response header). Minimum charge is 5 attach ($0.005) per message. Short messages settle below the estimate; long messages on premium models can settle above it — the estimate is a typical midpoint, not a cap. Failed requests and broken streams are fully refunded automatically.

🎯 Three Modes

Botstrapp.ai offers three interaction modes:

📡 API Endpoints

Chat

Models & Catalog

Auth

Billing & Credits

Partner Integration

🔐 Authentication

All API requests require a Bearer token in the Authorization header:

Authorization: Bearer bst_your_api_key_here

Your API key starts with bst_ and is generated when you create an account. Keep it secret — it controls access to your attach balance.

💎 attach Credits

Every API call costs attach, a closed-loop platform service credit. 1 attach = $0.001, so 1,000 attach = $1.00. New accounts receive 1,000 attach free. attach is non-monetary, non-transferable between users, and has no value outside Botstrapp.ai — see Terms § 5.

Buy more at botstrapp.ai/pricing or via the checkout API. Card + USDC accepted.

Bring your own key (BYOK)

Have your own provider API key? Use it with Botstrapp and the per-message attach price drops to 60% of the standard price.

Unlimited Mode

Toggle unlimited mode via POST /api/billing/unlimited or the ∞ checkbox in Chat. When active:

• No rate limits — RPM, RPD, and cost-per-day limits are removed
• Credits still deducted — you pay for what you use
• Auto-deactivates when balance drops below 1,000 attach ($1.00)

Designed for batch operations, character training, and heavy API usage.

🔧 Integration Example

Replace your existing OpenAI calls with Botstrapp.ai in 2 lines:

# Before (OpenAI only)
client = OpenAI(api_key="sk-...")

# After (Botstrapp.ai — access ALL models)
client = OpenAI(
    base_url="https://botstrapp.ai/v1",
    api_key="bst_...",
)

# Now you can use any model — same syntax:
client.chat.completions.create(model="gpt-4o", ...)
client.chat.completions.create(model="claude-sonnet-4-20250514", ...)
client.chat.completions.create(model="gemini/gemini-2.5-pro", ...)
client.chat.completions.create(model="groq/llama-3.3-70b-versatile", ...)

📦 Response Format

Responses follow the standard OpenAI format:

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "gpt-4o",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 9,
    "total_tokens": 21
  }
}

Cost headers

Every completion response includes cost headers so you can track spend per request:

❌ Error Codes