API Documentation

Quickstart

TamgaStudio is a fully OpenAI-compatible API gateway. All endpoints follow the OpenAI format. Just change the base_url and your API key.

curl https://tamga.studio/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tamgastudio/gpt-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Base URL: https://tamga.studio/api/v1

Authentication

All API requests require an API key passed as a Bearer token in the Authorization header.

Authorization: Bearer tl-sk-your-api-key-here

Generate API keys from the dashboard.

Chat Completions

Generate text responses from any of the available AI models.

Request Body

{
  "model": "tamgastudio/gpt-5",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is AI?"}
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "top_p": 1,
  "stream": false
}

Parameters

Streaming

Set stream: true for real-time SSE (Server-Sent Events) responses. Each chunk contains a delta of the generated content.

curl https://tamga.studio/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tamgastudio/gpt-5",
    "messages": [{"role": "user", "content": "Tell me a story"}],
    "stream": true
  }'

Stream ends with data: [DONE].

Models & Pricing

250+ AI models available. All models are accessed through the same API endpoint with consistent pricing. View the complete model catalog on the Models page.

GET /api/v1/models

Python SDK (OpenAI)

Use the official OpenAI Python library with TamgaStudio as the base URL.

pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="https://tamga.studio/api/v1",
    api_key="YOUR_API_KEY"
)

# Chat
response = client.chat.completions.create(
    model="tamgastudio/gpt-5",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

# Streaming
stream = client.chat.completions.create(
    model="tamgastudio/gpt-5",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

# Models list
models = client.models.list()
for m in models:
    print(m.id)

JavaScript / Node.js

const response = await fetch("https://tamga.studio/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "tamgastudio/gpt-5",
    messages: [{role: "user", content: "Hello!"}],
    stream: false
  })
});
const data = await response.json();
console.log(data.choices[0].message.content);

cURL Examples

# Chat
curl https://tamga.studio/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tamgastudio/gpt-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

# List models
curl https://tamga.studio/api/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Credits & Billing

TamgaStudio uses a prepaid credit system. Here is how it works:

• Deposit funds to your account to get started (minimum $5.00)
• Each API call deducts from your credit balance based on actual token usage x model pricing
• You can monitor your credit balance in the Billing Dashboard
• When your balance reaches $0, API requests return 402 Insufficient Credits
• Credit top-up Coming Soon

Check your balance via API:

curl https://tamga.studio/api/dashboard/billing \
  -H "Cookie: tamgastudio_session=YOUR_SESSION"

Rate Limits

Error Handling