Install

pip install the-token-company

Quick start

from thetokencompany import TheTokenCompany

client = TheTokenCompany(api_key="ttc-...")
result = client.compress("Your long prompt text here...", model="bear-2")

print(result.output)           # compressed text
print(result.tokens_saved)     # tokens removed
print(result.compression_ratio)  # e.g. 1.8

SDK wrappers

Drop-in wrappers that auto-compress conversation turns before sending to your LLM. By default every turn — user, system, tool, and assistant/agent — is compressed. To keep the provider's KV cache warm, pass a per-role aggressiveness dict that omits the assistant key (e.g. {"user": 0.2, "system": 0.2, "tool": 0.2}).

OpenAI / OpenRouter

from openai import OpenAI
from thetokencompany.openai import with_compression

client = with_compression(OpenAI(), compression_api_key="ttc-...")

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

Works with AsyncOpenAI too — the wrapper detects async automatically.

Anthropic

from anthropic import Anthropic
from thetokencompany.anthropic import with_compression

client = with_compression(Anthropic(), compression_api_key="ttc-...")

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    system="You are a helpful assistant...",
    messages=[{"role": "user", "content": "Summarize these results..."}],
)

Both messages and the system parameter are compressed.

Async

from thetokencompany import AsyncTheTokenCompany

async with AsyncTheTokenCompany(api_key="ttc-...") as client:
    result = await client.compress("Your long prompt text...")

Models

Aggressiveness

Control compression intensity with aggressiveness (0.0 – 1.0, default 0.5):

result = client.compress(text, model="bear-2", aggressiveness=0.8)

App ID

Tag compression requests with an application identifier for usage tracking:

# Set on the client — applies to all requests
client = TheTokenCompany(api_key="ttc-...", app_id="my-chatbot")

# Or per-request (overrides the client-level value)
result = client.compress(text, model="bear-2", app_id="my-chatbot")

Also supported in wrappers:

client = with_compression(OpenAI(), compression_api_key="ttc-...", app_id="my-chatbot")

Gzip

Enable gzip compression of request payloads for better performance on large inputs (up to 2.2x faster on 1M+ tokens):

client = TheTokenCompany(api_key="ttc-...", gzip=True)

Protect text from compression

Use protect() to wrap content in <ttc_safe> tags — protected text passes through unchanged:

from thetokencompany import protect

prompt = f"{protect('system:')} You are a helpful assistant.\n{protect('user:')} Hello!"
result = client.compress(prompt, model="bear-2")

Response

CompressResponse fields:

License

MIT