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
| Option | Type | Default |
|---|---|---|
apiKey | string | required |
model | string | llama-3.3-70b |
baseUrl | string | https://api.cerebras.ai/v1 |
retry | RetryOptions | inherited |
#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
| Var | Purpose |
|---|---|
CEREBRAS_API_KEY | API key |
#Related
Explore nearby
- PeerProviders
25 native chat and embedder adapters, plus higher-order adapters that compose candidates. Separate from the 140-provider models catalog.
- PeerChoosing an adapter
Capability decision table and rules of thumb for picking a chat adapter.
- PeerHosted chat adapters
17 managed-LLM adapters. Same contract; swap by changing one import.