Skip to main content

​
Overview

Cerebras provides an OpenAI-compatible API at https://api.cerebras.ai/v1 for fast inference. Some OpenAI parameters are not supported: frequency_penalty, logit_bias, presence_penalty, parallel_tool_calls, and service_tier. Model Class: CerebrasModel

​
Authentication

export CEREBRAS_API_KEY="..."

​
Examples

from upsonic import Agent, Task
from upsonic.models.cerebras import CerebrasModel

model = CerebrasModel(model_name="gpt-oss-120b")
agent = Agent(model=model)

task = Task("Hello, how are you?")
result = agent.do(task)
print(result)

​
Model Settings

You can set model parameters in two ways: on the model or on the Agent. On the model: 
from upsonic import Agent, Task
from upsonic.models.cerebras import CerebrasModel, CerebrasModelSettings

model = CerebrasModel(
    model_name="gpt-oss-120b",
    settings=CerebrasModelSettings(max_tokens=1024, temperature=0.7)
)
agent = Agent(model=model)
On the Agent: 
from upsonic import Agent, Task
from upsonic.models.cerebras import CerebrasModelSettings

agent = Agent(
    model="cerebras/gpt-oss-120b",
    settings=CerebrasModelSettings(max_tokens=1024, temperature=0.7)
)

​
Parameters

ParameterTypeDescriptionDefaultSource
max_tokensintMaximum tokens to generateModel defaultBase
temperaturefloatSampling temperature (0.0-2.0)1.0Base
top_pfloatNucleus sampling1.0Base
seedintRandom seedNoneBase
stop_sequenceslist[str]Stop sequencesNoneBase
timeoutfloatRequest timeout (seconds)600Base
Not supported by Cerebras: presence_penalty, frequency_penalty, logit_bias, parallel_tool_calls, service_tier. Omit these in settings when using the Cerebras provider.