Anthropic

Instrument Claude API calls with automatic token counting and cost tracking using the AgentVista Anthropic adapter.

The AnthropicAdapter extracts telemetry from Anthropic Message responses — model name, input and output token counts, and cost in USD — and passes them directly into agentvista.record() or a traced run. Cost is calculated automatically from the model name using AgentVista’s built-in pricing table; no manual configuration is required.

Setup

1. Install the SDK with the Anthropic extra

   pip install agentvista[anthropic]
   

   This installs agentvista along with the anthropic package.

2. Initialize AgentVista

   Call agentvista.init() once at application startup with your API key.

   import agentvista
   
   agentvista.init(api_key="av_xxxxx")
   
3. Import the adapter

   from agentvista.adapters.anthropic import AnthropicAdapter
   
   adapter = AnthropicAdapter()
   

Usage examples

Basic

Use adapter.extract() on any anthropic.types.Message response and unpack the result directly into agentvista.record().

import anthropic
import agentvista
from agentvista.adapters.anthropic import AnthropicAdapter

agentvista.init(api_key="av_xxxxx")
adapter = AnthropicAdapter()

client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Qualify this lead..."}],
)

# Extract model, input_tokens, output_tokens, total_tokens, cost_usd
telemetry = adapter.extract(response)
agentvista.record(agent="lead-qualifier", success=True, **telemetry)

adapter.extract() returns a dict with any of these keys present:

Key	Type	Description
model	str	Model ID returned by the API (e.g. "claude-sonnet-4-6-20260205")
input_tokens	int	Prompt tokens plus any cache creation and cache read tokens
output_tokens	int	Completion tokens
total_tokens	int	Sum of input and output tokens
cost_usd	float	Total cost in USD, rounded to 6 decimal places

With tracing

Wrap your Claude call in agentvista.run() to record a full traced run with outcome signals.

import anthropic
import agentvista
from agentvista.adapters.anthropic import AnthropicAdapter

agentvista.init(api_key="av_xxxxx")
adapter = AnthropicAdapter()
client = anthropic.Anthropic()

with agentvista.run("lead-qualifier") as r:
    response = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
        messages=[{"role": "user", "content": "Qualify this lead..."}],
    )

    telemetry = adapter.extract(response)
    agentvista.record(agent="lead-qualifier", success=True, **telemetry)

    qualified = "yes" in response.content[0].text.lower()
    r.set_outcome(success=qualified, outcome="qualified" if qualified else "not-qualified")

r.set_outcome(success, outcome) attaches a business-level result to the trace. The context manager automatically records duration and flushes the trace on exit.

Streaming

For streaming responses, call stream.get_final_message() to get the completed Message object and pass it to the adapter.

import anthropic
import agentvista
from agentvista.adapters.anthropic import AnthropicAdapter

agentvista.init(api_key="av_xxxxx")
adapter = AnthropicAdapter()
client = anthropic.Anthropic()

with client.messages.stream(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Summarize this document..."}],
) as stream:
    # Consume the stream however you need
    for text in stream.text_stream:
        print(text, end="", flush=True)

    # get_final_message() returns the complete Message with usage populated
    final_message = stream.get_final_message()

telemetry = adapter.extract(final_message)
agentvista.record(agent="summarizer", success=True, **telemetry)

Pass stream.get_final_message() — not the stream object itself — to adapter.extract(). The stream object does not expose usage data directly.

Supported models

Cost calculation is automatic for the following Claude models. If your model is not listed, cost_usd will be absent from the extracted telemetry; all other fields (tokens, model name) are still captured.

Model	Input (per M tokens)	Output (per M tokens)
claude-opus-4-6	$5.00	$25.00
claude-sonnet-4-6	$3.00	$15.00
claude-sonnet-4-5	$3.00	$15.00
claude-haiku-4-5	$1.00	$5.00
claude-opus-4-0	$15.00	$75.00
claude-haiku-3-5	$0.80	$4.00
claude-3-haiku	$0.25	$1.25

Models with prompt caching enabled (Opus 4.6, Sonnet 4.6, Sonnet 4.5, Haiku 4.5) also track cache_creation_input_tokens and cache_read_input_tokens from the Anthropic response and apply the correct cached read and cache write rates automatically.

The adapter matches both full versioned IDs (e.g. claude-sonnet-4-6-20260205) and short aliases (e.g. claude-sonnet-4-6).