← directory / providers / cerebras
Cerebras Inference
cloud3
models served
CEREBRAS_API_KEY
auth
api.cerebras.ai/v1
base url
Wafer-scale inference, very high tokens/sec; OpenAI-compatible. docs →
01Request template
Every model below is invoked with this shape — swap in the provider model ID from the table.
curl https://api.cerebras.ai/v1/chat/completions \
-H "Authorization: Bearer $CEREBRAS_API_KEY" \
-H "content-type: application/json" \
-d '{
"model": "{{MODEL_ID}}",
"messages": [{"role": "user", "content": "Hello, world"}]
}'02Models served · newest first
| Model | Provider model ID | In $/M | Out $/M | Context |
|---|---|---|---|---|
| gpt-oss-120bOpenAI | gpt-oss-120b | — | — | 131K |
| Qwen3 Coder 480BAlibaba Qwen | qwen-3-coder-480b | — | — | 262K |
| Llama 3.3 70BMeta | llama-3.3-70b | — | — | 131K |