API Overview

⚠️ BETA: GMTech's API is currently in beta testing. We welcome your feedback!

GMTech's API provides unified access to 15+ AI models through an OpenAI-compatible interface.

Why Use GMTech's API?

Single Interface, Multiple Providers

Access models from OpenAI, Anthropic, Google, Meta, and more through one API. No need to manage multiple SDKs or billing accounts.

OpenAI Drop-In Compatibility

# Replace OpenAI with GMTech
client = OpenAI(
    base_url="https://app.gmtech.com/api/v1",
    api_key="gmtech_..."
)
# Everything else works the same!

Key Benefits

Real-time cost tracking
Team-based billing
Transparent pricing (no markup)
15+ AI providers in one place

Supported Endpoints

Endpoint	Description
`/chat/completions`	Text generation (OpenAI compatible)
`/images/generations`	Image creation (OpenAI compatible)
`/models`	List available models

Available Models

Language Models

# OpenAI
"gpt-4o", "gpt-4-turbo", "gpt-3.5-turbo"

# Anthropic Claude
"claude-3-5-sonnet-20241022", "claude-3-5-haiku-20241022"

# Google Gemini
"gemini-1.5-pro", "gemini-1.5-flash"

# Meta Llama
"llama-3.1-405b-instruct", "llama-3.1-70b-instruct"

# Others
"command-r-plus", "mistral-large-latest"

Image Generation Models

"dall-e-3", "dall-e-2", "stable-diffusion-xl"

Quick Start

📸 API Response Example

Python code running with successful API response from GMTech

📸 SCREENSHOT NEEDED: api-response-terminal.png
What to capture: Terminal window showing Python API call and response
Show: Python code visible (client setup + chat completion), successful response printed, clear output showing it worked
Tips: Run a basic example, capture terminal with code + output visible

1. Get Your API Key

Visit API Keys in your dashboard to create a key.

2. Install OpenAI Library

pip install openai

3. Basic Chat Completion

from openai import OpenAI

client = OpenAI(
    base_url="https://app.gmtech.com/api/v1",
    api_key="your_gmtech_api_key"
)

response = client.chat.completions.create(
    model="gpt-4-turbo",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)

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

4. Try Different Models

# Use any supported model
response = client.chat.completions.create(
    model="claude-3-5-sonnet-20241022",  # Switch to Claude
    messages=[{"role": "user", "content": "Hello!"}]
)

5. Generate Images

image = client.images.generate(
    model="dall-e-3",
    prompt="A futuristic city with flying cars",
    size="1024x1024"
)

print(image.data[0].url)

Error Handling

from openai import APIError, AuthenticationError

try:
    response = client.chat.completions.create(...)
except AuthenticationError:
    print("Invalid API key")
except APIError as e:
    print(f"API error: {e}")

Rate Limits

Tier	Requests/min	Tokens/min
Free	60	40K
Pro	3,000	250K
Team	5,000	500K

Overview