Anthropic

How it works

Anthropic uses direct mode. Because Anthropic’s API is not OpenAI-compatible, Cognisafe wraps the messages.create method on the Anthropic client rather than routing through the proxy. After the model responds:

Your code receives the response immediately
The SDK fires a background task that ships the request and response payload to POST /internal/log on the FastAPI backend
The backend queues a scoring job in Redis

No proxy is involved. The background shipping adds no perceptible latency to your application.

Installation

pip install "cognisafe[anthropic]"

Setup

import cognisafe
import anthropic

cognisafe.configure(
    api_key="csk_your_key_here",
    project_id="my-app",
)
cognisafe.patch_anthropic()

client = anthropic.Anthropic()

message = client.messages.create(
    model="claude-opus-4-5",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Explain quantum entanglement in one paragraph."}
    ],
)

print(message.content[0].text)

Supported capabilities

Capability	Supported	Notes
Messages API (`messages.create`)	Yes	Full request and response logged
Streaming	Yes	Captured after stream completes
System prompts	Yes	Included in logged payload
Tool use	Yes	Tool definitions and results logged
Vision (image inputs)	Yes	Image payloads included in request body

Scoring note

Safety scoring always uses the model configured via SCORER_MODEL (default: gpt-4o-mini), regardless of which Claude model was used for the original call. The scorers are model-agnostic — they receive the text of the prompt and response, not a reference to the originating model.

Claude models and the scoring model are completely independent. You can use claude-opus-4-5 for your product and GPT-4o mini as the safety scorer with no conflict.

Async client

patch_anthropic() also wraps the async client:

import asyncio
import cognisafe
import anthropic

cognisafe.configure(api_key="csk_...", project_id="my-app")
cognisafe.patch_anthropic()

async def main():
    client = anthropic.AsyncAnthropic()
    message = await client.messages.create(
        model="claude-haiku-4-5",
        max_tokens=512,
        messages=[{"role": "user", "content": "Hello."}],
    )
    print(message.content[0].text)

asyncio.run(main())

Getting Started

SDKs

LLM Providers

Self-hosted Models

Self-hosting

Integrations

Reference Architectures

Deployment Blueprints

Safety & Scoring

How it works

Installation

Setup

Supported capabilities

Scoring note

Async client

​How it works

​Installation

​Setup

​Supported capabilities

​Scoring note

​Async client

How it works

Installation

Setup

Supported capabilities

Scoring note

Async client