Return to model library
Groq 2024-12-06
llama-3.3-70b-groq
超低延迟开源 · 实时聊天 / 语音
UniversaltextExtremely fast reasoning
数据政策 / Data Policy:未知 / Unknown
未经法务确认上游 ToS,不做承诺
查看 Groq 服务条款提示:此 provider 数据政策待法务审定;medical / legal 客户请联系商务确认 DPA。
context window
128K
tokens
maximum output
8.2K
tokens
knowledge cutoff
2023-12
Overall rating
7.71
/ 10
capability radar
code7.5
Mathematics7.0
reasoning7.5
creativity7.5
multilingual7.5
long context7.0
speed10.0
Pricing
input price$0.708000/ 1M tokens
output price$0.948000/ 1M tokens
Support features
Tool callStreaming output
Recommended scenarios
超低延迟开源
实时聊天 / 语音
Call example
Called via Nexevo.ai gateway — fully compatible with OpenAI SDK, just replace base URL
curl https://api.nexevo.ai/v1/chat/completions \
-H "Authorization: Bearer $NEXEVO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.3-70b-groq",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'