Llama 3.3 70B Instruct

Llama 3.3 70B Instruct is Meta's refined text-only model. It targets 405B-class results at 70B serving cost, with improved instruction following and multilingual capability. Your use subject to Meta's Terms & Privacy Policies.

Tool Use

Use with AI Gateway View docs

TypeScript

Python

import { streamText } from 'ai'

const result = streamText({
  model: 'meta/llama-3.3-70b',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview About Providers Throughput Latency Uptime Status Similar FAQ

More models by Meta

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Release Date

meta/muse-spark-1.1

5.6s

151tps

$1.25/M

$4.25/M

Read:$0.15/M

Write:—

—

07/09/2026

meta/llama-4-maverick

131K

0.2s

29tps

$0.24/M

$0.97/M

—

04/05/2025

meta/llama-4-scout

131K

0.2s

176tps

$0.17/M

$0.66/M

—

04/05/2025

meta/llama-3.1-8b

131K

0.1s

235tps

$0.02/M

$0.05/M

Read:$0.03/M

Write:—

—

07/23/2024

meta/llama-3.1-70b

131K

0.3s

74tps

$0.72/M

—

07/23/2024

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Llama 3.3 70B Instruct

More models by Meta