Cerebras LLM Inference
Conversation settings
Show
Hide
Model
llama-4-scout-17b-16e-instruct
llama3.1-8b
llama-3.3-70b
gpt-oss-120b
qwen-3-32b
Max tokens (optional)
Leave blank to let the API decide. Use -1 for unlimited tokens.
Temperature
0.7
Top P
0.9
System prompt (optional)
Conversation
Reset conversation
Start a conversation to see responses here.
Message
Press ⌘+Enter or Ctrl+Enter to send quickly.
Stop
Send