Skip to main content

​
OpenAI-Compatible API

Compile Labs provides full compatibility with the OpenAI API, making it easy to use any OpenAI-compatible model through our unified interface.

​
Chat Completions

curl https://api.compilelabs.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5",
    "messages": [
      {"role": "user", "content": "Hello, how are you?"}
    ],
    "temperature": 0.7,
    "max_tokens": 100
  }'

​
Streaming Responses

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

​
Using OpenAI Python SDK

import openai

client = openai.OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.compilelabs.com/v1"
)

response = client.chat.completions.create(
    model="openai/gpt-5",
    messages=[
        {"role": "user", "content": "Explain quantum computing"}
    ]
)

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

​
Streaming with Python SDK

import openai

client = openai.OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.compilelabs.com/v1"
)

stream = client.chat.completions.create(
    model="openai/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="")

​
System Prompts

response = client.chat.completions.create(
    model="openai/gpt-5",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Write a Python function to calculate fibonacci numbers"}
    ],
    temperature=0.7,
    max_tokens=500
)

​
Multi-Turn Conversations

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is the capital of France?"},
    {"role": "assistant", "content": "The capital of France is Paris."},
    {"role": "user", "content": "What is its population?"}
]

response = client.chat.completions.create(
    model="openai/gpt-5",
    messages=messages
)

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

​
Using Different Models

Compile Labs supports multiple OpenAI-compatible models: 
# OpenAI models
gpt_response = client.chat.completions.create(
    model="openai/gpt-5",
    messages=[{"role": "user", "content": "Hello!"}]
)

# Meta models
llama_response = client.chat.completions.create(
    model="moonshotai/kimi-k2-0905",
    messages=[{"role": "user", "content": "Hello!"}]
)

# DeepSeek models
deepseek_response = client.chat.completions.create(
    model="deepseek/deepseek-v3",
    messages=[{"role": "user", "content": "Hello!"}]
)

​
List Available Models

curl "https://api.compilelabs.com/v1/models?type=text_to_text" \
  -H "Authorization: Bearer YOUR_API_KEY"

​
SDK Compatibility

Compile Labs is compatible with:
  • OpenAI SDK (openai Python package)
  • Any OpenAI-compatible library (LlamaIndex, LangChain, etc.)
Use your existing OpenAI SDK code with Compile Labs - just change the base_url to https://api.compilelabs.com/v1 and you’re ready to go!

​
Next Steps

Image Generation

Generate images with AI models

Chat Completions

Deep dive into chat functionality

API Reference

Browse complete API documentation