Skip to main content
Cerebras provides high-speed OpenAI-compatible inference on custom inference hardware. The plugin ships a static four-model catalog (no live discovery).
PropertyValue
Provider idcerebras
Pluginofficial external package (@openclaw/cerebras-provider)
Auth env varCEREBRAS_API_KEY
Onboarding flag--auth-choice cerebras-api-key
Direct CLI flag--cerebras-api-key <key>
APIOpenAI-compatible (openai-completions)
Base URLhttps://api.cerebras.ai/v1
Default modelcerebras/zai-glm-4.7

​
Install plugin

openclaw plugins install @openclaw/cerebras-provider
openclaw gateway restart

​
Getting started

1

Get an API key

Create an API key in the Cerebras Cloud Console.
2

Run onboarding

openclaw onboard --auth-choice cerebras-api-key

openclaw onboard --non-interactive \
  --auth-choice cerebras-api-key \
  --cerebras-api-key "$CEREBRAS_API_KEY"

export CEREBRAS_API_KEY=csk-...
3

Verify models are available

openclaw models list --provider cerebras
Lists all four static models. If CEREBRAS_API_KEY is unresolved, openclaw models status --json reports the missing credential under auth.unusableProfiles.

​
Non-interactive setup

openclaw onboard --non-interactive \
  --mode local \
  --auth-choice cerebras-api-key \
  --cerebras-api-key "$CEREBRAS_API_KEY"

​
Built-in catalog

All four models share a 128k context window and 8,192 max output tokens.
Model refNameReasoningNotes
cerebras/zai-glm-4.7Z.ai GLM 4.7yesDefault model; preview reasoning model
cerebras/gpt-oss-120bGPT OSS 120ByesProduction reasoning model
cerebras/qwen-3-235b-a22b-instruct-2507Qwen 3 235B InstructnoPreview non-reasoning model
cerebras/llama3.1-8bLlama 3.1 8BnoProduction speed-focused model
Cerebras marks zai-glm-4.7 and qwen-3-235b-a22b-instruct-2507 as preview models, and llama3.1-8b plus qwen-3-235b-a22b-instruct-2507 are documented for deprecation on May 27, 2026. Check Cerebras’ supported-models page before relying on them for production workloads.

​
Manual config

Most setups only need the API key. Use explicit models.providers.cerebras config to override model metadata or run in mode: "merge" against the static catalog: 
{
  env: { CEREBRAS_API_KEY: "csk-..." },
  agents: {
    defaults: {
      model: { primary: "cerebras/zai-glm-4.7" },
    },
  },
  models: {
    mode: "merge",
    providers: {
      cerebras: {
        baseUrl: "https://api.cerebras.ai/v1",
        apiKey: "${CEREBRAS_API_KEY}",
        api: "openai-completions",
        models: [
          { id: "zai-glm-4.7", name: "Z.ai GLM 4.7" },
          { id: "gpt-oss-120b", name: "GPT OSS 120B" },
        ],
      },
    },
  },
}
If the Gateway runs as a daemon (launchd, systemd, Docker), make sure CEREBRAS_API_KEY is available to that process — for example in ~/.openclaw/.env or through env.shellEnv. A key exported only in an interactive shell will not help a managed service unless the env is imported separately.

Model providers

Choosing providers, model refs, and failover behavior.

Thinking modes

Reasoning effort levels for the two reasoning-capable Cerebras models.

Configuration reference

Agent defaults and model configuration.

Models FAQ

Auth profiles, switching models, and resolving “no profile” errors.