TTC Router

The TTC Router is a drop-in replacement for the OpenAI /chat/completions endpoint. Every message is automatically compressed before being forwarded to your chosen LLM provider — no extra code needed.

Usage

Point the OpenAI SDK at our base URL and prefix your model with the provider name.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.thetokencompany.com/v1",
    api_key="ttc-...",
)

response = client.chat.completions.create(
    model="openai/gpt-5.4",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Your long prompt goes here..."},
    ],
)

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

Supported models

Streaming

Full SSE streaming support — works exactly like the OpenAI SDK.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.thetokencompany.com/v1",
    api_key="ttc-...",
)

stream = client.chat.completions.create(
    model="openai/gpt-5.4",
    messages=[{"role": "user", "content": "Your long prompt..."}],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

How it works

1. You send a standard chat completions request
2. All messages are compressed automatically
3. The compressed request is forwarded to the LLM provider
4. The response is returned with token usage stats

Features

• OpenAI SDK compatible — works with the Python and Node SDKs
• All messages compressed — system, user, and assistant messages are all optimized
• Streaming — full SSE streaming support
• Multimodal — text parts are compressed; images pass through unchanged
• Tools & function calling — fully supported
• Automatic caching — repeated messages are served from cache