Anthropic

Anthropic Claude is an LLM plugin. It takes the transcribed conversation and generates the reply, with support for tool calling, prompt caching, and extended thinking.

Setup

Set your Anthropic API key in the worker environment. Generate a key from the Anthropic console:

export ANTHROPIC_API_KEY=<key>

Usage

Import the plugin and pass it to the pipeline’s llm slot.

from zeroruntime.plugins import AnthropicLLM

llm = AnthropicLLM(
    model="claude-sonnet-4-20250514",
    temperature=0.7,
)

# Pipeline(llm=llm, ...)

import { AnthropicLLM } from '@zeroruntime/js-sdk/plugins';

const llm = AnthropicLLM({
  model: 'claude-sonnet-4-20250514',
  temperature: 0.7,
});

// Pipeline({ llm, ... })

Configuration Options

Constructor parameters for AnthropicLLM. The Python and Node JS SDKs share these field names.

Core

Parameter	Type	Default	Description
`api_key`	`str`	`None`	Anthropic API key. Falls back to the `ANTHROPIC_API_KEY` environment variable when unset.
`model`	`str`	`"claude-sonnet-4-20250514"`	Claude model used to generate replies.
`temperature`	`float`	`0.7`	Sampling randomness; lower is more deterministic.
`max_output_tokens`	`int`	`1024`	Maximum number of tokens the model may generate per response. The legacy `max_tokens` kwarg is accepted as a deprecated alias.

Sampling

Parameter	Type	Default	Description
`top_k`	`int`	`None`	Top-k sampling cutoff.
`top_p`	`float`	`None`	Nucleus-sampling probability cutoff.
`stop_sequences`	`str` or `list[str]`	`None`	One or more strings at which the model stops generating. Accepts a single string or a list of strings.

Advanced

Parameter	Type	Default	Description
`thinking_budget`	`int`	`None`	Token budget for Claude’s extended thinking (chain-of-thought reasoning). A positive value (e.g. `1024`) enables thinking; `None` disables it. The legacy `thinking={"budget_tokens": N}` dict form is also accepted.

For voice, short replies feel best. Keep max_output_tokens modest and the system instruction concise to keep latency down.

Import paths

SDK	Import	Constructor
Python	`from zeroruntime.plugins import AnthropicLLM`	`AnthropicLLM(...)`
Node JS	`import { AnthropicLLM } from '@zeroruntime/js-sdk/plugins'`	`AnthropicLLM({ ... })`

The reply is streamed to the text-to-speech plugin, which synthesizes the agent’s voice.

Plugins

Inference Gateway

Speech-to-text

LLM

Text-to-speech

Realtime models

Avatars

Turn detection

Voice activity detection

Noise cancellation

Setup

Usage

Configuration Options

Core

Sampling

Advanced

Import paths

​Setup

​Usage

​Configuration Options

​Core

​Sampling

​Advanced

​Import paths

Setup

Usage

Configuration Options

Core

Sampling

Advanced

Import paths