Skip to main content

​
AnthropicLLM

Anthropic (Claude) large language model provider. Creates a configured Anthropic LLM provider for use in a voice agent.

​
Constructor

​
apiKey
string
Anthropic API key. Falls back to the ANTHROPIC_API_KEY env var.
​
model
AnthropicLLMModel | string
Model ID to use. Default: 'claude-sonnet-4-20250514'.
​
temperature
number
Sampling temperature. Range 0-1. Default: 0.7.
​
maxOutputTokens
number
Maximum number of tokens to generate in the response. Default: 1024.
​
topP
number | null
Nucleus sampling probability mass. Default: null (provider default).
​
topK
number | null
Top-K sampling cutoff. Default: null (provider default).
​
stopSequences
string[] | string | null
Sequence(s) that stop generation when produced. Default: null.
​
thinkingBudget
number | null
Extended-thinking token budget. Default: null (disabled).

​
cancelCurrentGeneration

Cancel the in-flight generation for the current session, if any.

​
chat

Stream a completion for the given messages, yielding LLMResponse chunks.
​
returns
AsyncIterator<LLMResponse>

​
close

Release any resources held by the provider.

​
closeEmitter

Close the emitter: drop all handlers and stop emitting. Waits up to 2 seconds for in-flight async handlers to settle before returning.

​
emit

​
event
string
required

​
getRuntimeConfig

​
returns
Record<string, any>

​
listenerCount

​
event
string
required
​
returns
number

​
off

​
event
string
required
​
handler
EventHandler
required

​
on

​
event
string
required
​
handler
EventHandler
required
​
returns
EventHandler

​
once

​
event
string
required
​
handler
EventHandler
required
​
returns
EventHandler

​
removeAllListeners

​
event
string

​
AnthropicLLMModel