AI API Gateway

All Models, One Gateway

Same Code, Any Model

Switch Between Models Instantly

from openai import OpenAI

client = OpenAI(
    base_url="https://api.skillboss.co/v1",
    api_key="YOUR_SKILLBOSS_KEY"
)

# Use GPT-4o
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}]
)

# Or Claude Sonnet (just change model name!)
response = client.chat.completions.create(
    model="claude-sonnet-4-5-20250514",
    messages=[{"role": "user", "content": "Hello"}]
)

# Or Gemini Pro
response = client.chat.completions.create(
    model="gemini-2.5-pro",
    messages=[{"role": "user", "content": "Hello"}]
)

# Or DeepSeek R1 (78% cheaper)
response = client.chat.completions.create(
    model="deepseek-r1",
    messages=[{"role": "user", "content": "Hello"}]
)

Image Generation

response = client.images.generate(
    model="flux-1.1-pro",
    prompt="A serene mountain landscape at sunset",
    size="1024x1024"
)

image_url = response.data[0].url

Text-to-Speech

response = client.audio.speech.create(
    model="elevenlabs-tts",
    voice="alloy",
    input="Hello, this is a test of text to speech."
)

response.stream_to_file("output.mp3")

Why Use an AI Gateway

• No vendor lock-in — Switch between GPT, Claude, Gemini instantly
• One API key for everything — LLMs, images, audio, video, embeddings
• OpenAI-compatible — Works with existing OpenAI SDK code
• Cost optimization — Choose cheapest model for each task
• Automatic fallbacks — If one provider is down, switch to backup
• Unified billing — One invoice, one dashboard for all usage
• Works with your tools — Claude Code, Cursor, Windsurf, Aider
• Pay-as-you-go — No setup fees, no monthly minimums

Common Use Cases