API Reference

Authentication

All API requests require authentication via an API key. Include your API key in the Authorization header using the Bearer scheme.

Authorization: Bearer tl-sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

You can manage your API keys from the Dashboard. Keep your API keys secure and never expose them in client-side code.

Base URL

https://api.tamgalabs.com/v1

Chat Completions

https://api.tamgalabs.com/v1/chat/completions

Creates a model response for a given chat conversation. Compatible with the OpenAI chat completions format.

Request Body

{
  "model": "llama-3.1-405b",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is AI infrastructure?"}
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "stream": false
}

Example: cURL

curl https://api.tamgalabs.com/v1/chat/completions \
  -H "Authorization: Bearer tl-sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.1-405b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example: Python

from openai import OpenAI

client = OpenAI(
  base_url="https://api.tamgalabs.com/v1",
  api_key="tl-sk-xxxxxxxx"
)

response = client.chat.completions.create(
  model="llama-3.1-405b",
  messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

Example: JavaScript

const response = await fetch('https://api.tamgalabs.com/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer tl-sk-xxxxxxxx',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'llama-3.1-405b',
    messages: [{ role: 'user', content: 'Hello!' }]
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

Embeddings

https://api.tamgalabs.com/v1/embeddings

Creates an embedding vector representing the input text. Compatible with the OpenAI embeddings format.

Request Body

{
  "model": "text-embedding-3-large",
  "input": "The quick brown fox jumps over the lazy dog"
}

Example

curl https://api.tamgalabs.com/v1/embeddings \
  -H "Authorization: Bearer tl-sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-large",
    "input": "Hello world"
  }'

Images

https://api.tamgalabs.com/v1/images/generations

Generates images from text descriptions using supported diffusion models.

Request Body

{
  "model": "stable-diffusion-3",
  "prompt": "A serene mountain landscape at sunset",
  "n": 1,
  "size": "1024x1024"
}

Rerank

https://api.tamgalabs.com/v1/rerank

Reranks documents based on relevance to a query. Ideal for RAG pipelines and search.

Request Body

{
  "model": "rerank-multilingual-v2",
  "query": "What is machine learning?",
  "documents": [
    "Machine learning is a subset of artificial intelligence.",
    "Python is a programming language.",
    "Neural networks are inspired by the brain."
  ],
  "top_n": 2
}

List Models

https://api.tamgalabs.com/v1/models

Lists all available models for inference.

Example Response

{
  "object": "list",
  "data": [
    {"id": "llama-3.1-405b", "object": "model", "created": 1720000000, "owned_by": "tamgalabs"},
    {"id": "mistral-large-2", "object": "model", "created": 1720000000, "owned_by": "tamgalabs"},
    {"id": "stable-diffusion-3", "object": "model", "created": 1720000000, "owned_by": "tamgalabs"}
  ]
}