Cerebras - LangWatch

Add the credential

Open Settings > Model Providers, click Add Model Provider and select Cerebras. Give the row a name, pick the organization, team or project it belongs to, and fill in:

Field	Value
`CEREBRAS_API_KEY`	Your Cerebras API key.

Save the row. Every virtual key whose scope can see the row can now dispatch to it, unless the key restricts its providers. See Virtual keys.

The Cerebras model provider drawer with the CEREBRAS_API_KEY field and the routing handle cerebras — The Cerebras row: name, scope, CEREBRAS_API_KEY and the routing handle cerebras.

Model names

Write cerebras/<model>, for example cerebras/llama-3.3-70b. The gateway does not infer Cerebras from a bare name.

Send a request

curl https://gateway.langwatch.ai/v1/chat/completions \
  -H "Authorization: Bearer $LANGWATCH_VIRTUAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cerebras/llama-3.3-70b",
    "messages": [{"role": "user", "content": "Say hi in one word"}]
  }'

Endpoints

Endpoint	Served
`POST /v1/chat/completions`	Yes
`POST /v1/messages`	Yes, translated
`GET /v1/models`	Yes, from the Cerebras catalog

Last modified on September 6, 2026