LLMs
Cerebras
Portkey provides a robust and secure gateway to facilitate the integration of various Large Language Models (LLMs) into your applications, including the models hosted on Cerebras Inference API.
Provider Slug: cerebras
Portkey SDK Integration with Cerebras
Portkey provides a consistent API to interact with models from various providers. To integrate Cerebras with Portkey:
1. Install the Portkey SDK
2. Initialize Portkey with Cerebras
Authorization
: Pass your Cerebras API key with theAuthorization
param.custom_host
: Set the target Cerebras API URL tohttps://api.cerebras.ai/v1
.provider
: Since Cerebras follows the OpenAI schema, set the reference provider asopenai
.
3. Invoke Chat Completions
Supported Models
Cerebras currently supports Llama-3.1-8B
and Llama-3.1-70B
. You can find more info here:
Next Steps
The complete list of features supported in the SDK are available on the link below.
SDK
You’ll find more information in the relevant sections: