Anthropic — TokenID

Usage

from tokenid import JournaledAnthropic

client = JournaledAnthropic(
    api_key="sk-ant-…",          # your Anthropic key
    session_id="my-session",      # groups calls in your dashboard
)

response = client.messages.create(
    model="claude-opus-4-7",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}]
)

JournaledAnthropic accepts every argument that anthropic.Anthropic accepts. All methods are available.

Prompt caching

Prompt cache tokens (cache_read, cache_creation) are captured automatically from response.usage.

Tool use

Tool calls and tool results are captured as separate event fields: tool_name, tool_input, tool_output.

Streaming

with client.messages.stream(
    model="claude-opus-4-7",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}]
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

Async

Use AsyncJournaledAnthropic for async code:

import asyncio
from tokenid import AsyncJournaledAnthropic

async def main():
    client = AsyncJournaledAnthropic(api_key="sk-ant-…", session_id="my-session")
    resp = await client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(resp.content[0].text)

asyncio.run(main())

Parameters

Parameter	Type	Required	Description
`api_key`	string	Yes	Your Anthropic API key
`session_id`	string	No	Groups calls into a named session in your dashboard
`enforcement_config`	dict	No	Local enforcement rules (see Enforcement)