agentskit.js
Providers

cerebras

Cerebras — wafer-scale chips, OpenAI-compatible. Sub-100ms first-token latency on Llama / Qwen.

import { cerebras } from '@agentskit/adapters'

const adapter = cerebras({
  apiKey: process.env.CEREBRAS_API_KEY!,
  model: 'llama-3.3-70b',
})

#Options

OptionTypeDefault
apiKeystringrequired
modelstringllama-3.3-70b
baseUrlstringhttps://api.cerebras.ai/v1
retryRetryOptionsinherited

#Capabilities

{ streaming: true, tools: true, usage: true }. OpenAI-compatible — request shape matches openai({ baseUrl }).

#Why cerebras

  • Wafer-scale inference — among the fastest tokens-per-second on the market.
  • OpenAI-compatible endpoint, drop-in for existing OpenAI code.

#Env

VarPurpose
CEREBRAS_API_KEYAPI key

Explore nearby

✎ Edit this page on GitHub·Found a problem? Open an issue →·How to contribute →

On this page