Connect

One line. Full visibility.

Drop erabot into any LLM app via proxy or SDK — no code restructuring required.

Zero Infrastructure Changes

One line change. Full visibility.

Add a single base_url parameter to any existing OpenAI-compatible client.

main.pypython

# Before
import openai
client = openai.OpenAI(api_key="sk-...")
 
# After — add base_url
import openai
client = openai.OpenAI(
  api_key="sk-...",
  base_url="https://api.erabot.ai/v1",  # ← add this
)

Python SDK

Or use the SDK decorator

Wrap any function that calls an LLM. erabot tracks every call, attributes costs to your project, and reports savings automatically.

handlers.pypython

from erabot import track
 
@track(project="my-chatbot")
def generate_response(prompt: str) -> str:
    return client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": prompt}]
    ).choices[0].message.content

Zero config

No YAML, no env setup. Just import and decorate.

Per-call attribution

See exact costs broken down by function, model, and project.

Works with any LLM

OpenAI, Anthropic, Gemini, Mistral, Cohere, and 10+ more.

providers supported

OpenAI, Anthropic, Google, Mistral, Cohere & more

<1ms

proxy overhead

Negligible impact — your users won't notice a thing

100%

OpenAI-compatible

Drop-in replacement — no SDK changes needed

Ready to see it in action?

Scan your codebase in under 60 seconds. No credit card required.

erabot.ai

Back to Overview