Mistral 7B Instruct

Mistral AI · 7B params · 32k context

Deploy this modelrocket_launch
P
Parthexpand_more

About

Long-context, Apache-licensed instruct model. Strong for agentic workloads.

Type

Chat

Parameters

7B params

Context

32k

License

Apache 2.0

Recommended deployment

memory

Best quality

A100 PCIe 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

$0.08

per 1M tokens

Output tokens

$0.25

per 1M tokens

Quick stats

Deploys

3,120

Recommended GPU

A100 PCIe

Inference latency

~280ms P50

Throughput

~12k tok/s

Use cases

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