OpenAI-compatible API. One key, every major AI model. Drop-in replacement for OpenAI, Anthropic, Google, and more.
Botstrapp.ai is fully OpenAI-compatible. Use any OpenAI SDK โ just change the base URL and API key.
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)
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 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!"}] }'
Access models from 10+ providers through a single API. Use GET /v1/catalog for the live list.
| Tier | Cost per message | Example Models |
|---|---|---|
| Budget | 9 ICO (~$0.009) | Gemini Flash, GPT-5 Mini, Llama 3.3, Claude Haiku, Qwen 3 30B, DeepSeek V3, Phi-4 |
| Standard | 19 ICO (~$0.019) | GPT-5, Claude Sonnet 4.6, Gemini Pro, Grok 3, Qwen 3 235B, Moonshot Kimi K2 |
| Premium | 49 ICO (~$0.049) | Claude Opus 4.6, GPT-5 Turbo, DeepSeek R1, Grok 3 Reasoning |
GET /v1/models or GET /v1/catalog for detailed info including providers and availability status. The catalog is the single source of truth โ it powers the Chat UI and Pricing page dynamically.
Botstrapp.ai offers three interaction modes:
| Mode | model value | Description |
|---|---|---|
| ๐ก Connector | Any model ID | You pick the model. Direct connection to the provider. |
| ๐ Router | "strap" | Context-aware routing โ picks the best model based on your conversation history. |
| โก Strap | "strap" | Smart routing โ we pick the best model for your message automatically. |
| ๐ญ LCM | "lcm" | Large Character Model โ AI with persistent personality and memory. |
Send a chat message and get a response. Supports streaming.
| Parameter | Type | Description |
|---|---|---|
model required | string | Model ID, "strap" for smart routing, or "lcm" for character mode |
messages required | array | Array of message objects: {"role": "user"|"assistant"|"system", "content": "..."} |
stream | boolean | Enable SSE streaming (default: false) |
temperature | number | Sampling temperature 0-2 (default: model-specific) |
max_tokens | integer | Maximum output tokens |
List available models (OpenAI-compatible format).
Rich model catalog with providers, tiers, availability. Add ?show_all=true for all models.
Create account. Body: {"email", "password", "birth_year"}. Returns API key + 1,000 ICO bonus.
Login. Body: {"email", "password"}. Returns API key + balance.
Get current user profile and balance.
Get ICO balance, tier, and unlimited status.
Toggle unlimited mode. Body: {"enabled": true}. Removes rate limits; credits still apply. Auto-deactivates when balance < 1,000 ICO.
Create Stripe checkout. Body: {"package_id": "starter"|"plus"|"pro"|"ultra"}.
Get ICO cost per model (pattern matching rules).
Public ICO pricing โ single source of truth for partner platforms (e.g., Gamind.net). Returns packages, exchange rate, and bonus tiers.
Estimate cost before sending. Params: ?model=gpt-5&input_tokens=1000&output_tokens=500
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 โ it controls access to your ICO credits.
Every API call costs ICO credits. 1 ICO = $0.001. New accounts receive 1,000 ICO free.
Buy more credits at botstrapp.ai/pricing or via the checkout API.
Toggle unlimited mode via POST /v1/billing/unlimited or the โ checkbox in Chat. When active:
Designed for batch operations, character training, and heavy API usage.
Replace your existing OpenAI calls with Botstrapp.ai in 2 lines:
# Before (OpenAI only) client = OpenAI(api_key="sk-...") # After (Botstrapp.ai โ access ALL models) client = OpenAI( base_url="https://botstrapp.ai/v1", api_key="bst_...", ) # Now you can use any model โ 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", ...)
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
}
}
| Code | Meaning |
|---|---|
401 | Invalid or missing API key |
402 | Insufficient ICO credits |
429 | Rate limit exceeded (activate unlimited mode to bypass) |
400 | Bad request (missing model or messages) |
503 | Model temporarily unavailable |
Need help? support@botstrapp.ai