workers-ai
/
llama-3.1-8b
❯
ready
Ask anything. Responses stream from Workers AI.
◇
How does streaming work?
◇
Write a debounce utility
◇
Which model for code?
Enter
send
⇧Enter
newline
Esc
stop
⌘K
clear
⌘/
settings
❯
idle
⏺
llama-3.1-8b
⑂
main
▦
0%
$
$0.000
⚡
normal
Settings
Model
DeepSeek V4 Pro · 1M ctx
DeepSeek V4 Flash · 1M ctx
GPT-OSS 120B · 128k ctx
GPT-OSS 20B · 128k ctx
Kimi K2.7 Code · 262k ctx
Kimi K2.6 · 262k ctx · vision
Qwen 3.8 27B · 262k ctx
GLM-4.7 Flash · 131k ctx
Gemma 4 26B
Llama 4 Scout · vision
Nemotron 3 · 120B MoE
Llama 3.3 70B · balanced
Llama 3.1 8B · fast
System prompt
Temperature
0.7
Max tokens
2048