Llama 3 70B Instruct

Meta · 70B params · 8k context

Deploy this modelrocket_launch
P
Parthexpand_more

About

Meta's flagship open-source chat model. Excellent reasoning and instruction following.

Type

Chat

Parameters

70B params

Context

8k

License

Llama 3 Community

Recommended deployment

memory

Best quality

H100 SXM x8 · 12k tok/s

$26.4

/hour

memory

Balanced

A100 SXM x4 · 6k tok/s

$6.6

/hour

memory

Budget

RTX 4090 x2 · 2k tok/s

$1.1

/hour

Pricing

Input tokens

$0.60

per 1M tokens

Output tokens

$1.80

per 1M tokens

Quick stats

Deploys

2,410

Recommended GPU

H100 SXM

Inference latency

~280ms P50

Throughput

~12k tok/s

Use cases

  • check_circleCustomer support automation
  • check_circleKnowledge base search
  • check_circleAgentic workflows
  • check_circleContent generation