Skip to main content

CerebrasLLM

Cerebras large language model provider. Creates a configured Cerebras LLM provider for use in a voice agent.

Constructor

apiKey
string
Cerebras API key. Falls back to the CEREBRAS_API_KEY env var.
model
CerebrasLLMModel | string
Model ID. Default: 'llama3.3-70b'.
temperature
number
Sampling temperature. Default: 0.7.
toolChoice
string
Tool-selection strategy, e.g. 'auto', 'none'. Default: 'auto'.
maxCompletionTokens
number
Maximum number of completion tokens to generate. Default: 1024.
topP
number
Nucleus sampling probability mass. Default: null.
seed
number
Sampling seed for reproducible outputs. Default: null.
stop
string
Stop sequence. Default: null.
user
string
Opaque end-user identifier. Default: null.

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

CerebrasLLMModel