Skip to content

Llama 3.1 70B Instruct

Llama 3.1 70B Instruct introduced context of 131.1K tokens, eight-language multilingual support, and trained tool-use capability to the open 70B parameter class. This release defined Meta's approach to open frontier models.

Tool Use
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'meta/llama-3.1-70b',
prompt: 'Why is the sky blue?'
})

More models by Meta

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Per Query
Capabilities
Providers
ZDR
No Training
Release Date
131K
0.2s
36tps
$0.24/M$0.97/M
bedrock logo
deepinfra logo
04/05/2025
131K
0.2s
199tps
$0.17/M$0.66/M
bedrock logo
deepinfra logo
groq logo
04/05/2025
128K
0.3s
109tps
$0.59/M$0.72/M
bedrock logo
groq logo
12/06/2024
128K
0.2s
51tps
$0.15/M$0.15/M
bedrock logo
09/18/2024
128K
0.2s
88tps
$0.10/M$0.10/M
bedrock logo
09/18/2024
131K
0.1s
160tps
$0.02/M$0.05/M
Read:$0.03/M
Write:
bedrock logo
deepinfra logo
groq logo
+1
07/23/2024