Cerebras()
Open-weight models at very high throughput, with your own API key. Costs go direct to the vendor at their rates — no markup, nothing on your Axon balance.
export default defineProfile({
providers: [Cerebras()],
})
Serves a fixed list — see below.
Credentials
Set the environment variable, or pass key on the declaration:
CEREBRAS_API_KEY=...
providers: [Cerebras({ key: process.env.MY_OWN_VAR })]
You can also store this key in your Axon account vault through the cloud client:
await cloud.user.vault.connections.get("cerebras").connect({ key: apiKey })
A fresh host signed into the same account can use the connection. Profiles without
an explicit providers list discover active account connections automatically;
an explicit list continues to restrict which providers that machine uses.
Explicit keys and environment variables take precedence over the account vault.
A custom url requires an explicit credential. Provider SDKs ship with Axon.
Options
Cerebras(options?: ProviderOptions)
| Option | Default | Description |
|---|---|---|
key | CEREBRAS_API_KEY | Your own credential, passed directly |
url | the provider's API | Endpoint override |
slots | unbounded | Ceiling on concurrent calls a fanned-out role may spend here |
An inference host, not a vendor
Like Groq(), Cerebras serves other vendors' open weights
under its own names, so this provider serves an explicit list rather than deriving
them. Currently mapped: GPT-OSS 120B and Gemma 4 31B.
A model absent from the list is not offered rather than guessed at — see Groq for why that is the right failure.
Model ids
Cerebras's own names:
export default defineAgent({ model: "cerebras:gpt-oss-120b" })