Meta logo

Llama-3.3-70B-Instruct

meta/llama-3.3-70b-instruct

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

Source-linkedllamaOpen weightsReleased 2024-12-06
Report data
Context window128K
Maximum output4.096K
Provider offers16
Knowledge cutoff2023-12
Capabilities

What this model supports

ReasoningNo
Tool callingYes
Structured outputNo
AttachmentsYes
Temperature controlYes
Open weightsYes
Creator
Meta
Family
llama
Modalities
Text
License
Not documented
Release date
2024-12-06
Model ID
meta/llama-3.3-70b-instruct
Market availability

Provider pricing

Report price →
Providers offering Llama-3.3-70B-Instruct
ProviderProvider model IDContextInput / 1MOutput / 1MCached / 1MFeaturesAll pricing
GitHub Modelsmeta/llama-3.3-70b-instruct128K$0.000$0.000R T ·
View
{
  "input": 0,
  "output": 0
}
Llamallama-3.3-70b-instruct128K$0.000$0.000· T ·
View
{
  "input": 0,
  "output": 0
}
Vercel AI Gatewaymeta/llama-3.3-70b128K$0.000$0.000· T ·
View
{
  "input": 0,
  "output": 0
}
Nvidiameta/llama-3.3-70b-instruct128K$0.000$0.000· T S
View
{
  "input": 0,
  "output": 0
}
Snowflake Cortexsnowflake-llama3.3-70b128K· T ·
View
{}
OpenRoutermeta-llama/llama-3.3-70b-instruct131.072K$0.100$0.320· T S
View
{
  "input": 0.1,
  "output": 0.32
}
LLM Gatewayllama-3.3-70b-instruct131.072K$0.130$0.400· T ·
View
{
  "input": 0.13,
  "output": 0.4
}
Neonmeta-llama-3-3-70b-instruct128K$0.500$1.500· T ·
View
{
  "input": 0.5,
  "output": 1.5
}
Abacusmeta-llama/Meta-Llama-3.3-70B-Instruct131.072K$0.590$0.790· T ·
View
{
  "input": 0.59,
  "output": 0.79
}
Hugging Facemeta-llama/Llama-3.3-70B-Instruct131.072K$0.590$0.790· T S
View
{
  "input": 0.59,
  "output": 0.79
}
Azurellama-3.3-70b-instruct128K$0.710$0.710· T ·
View
{
  "input": 0.71,
  "output": 0.71
}
Azure Cognitive Servicesllama-3.3-70b-instruct128K$0.710$0.710· T ·
View
{
  "input": 0.71,
  "output": 0.71
}
Scalewayllama-3.3-70b-instruct100K$0.900$0.900· T ·
View
{
  "input": 0.9,
  "output": 0.9
}
Pioneermeta-llama/Llama-3.3-70B-Instruct131.072K$0.900$0.900$0.900R T ·
View
{
  "cache_read": 0.9,
  "cache_write": 0.9,
  "input": 0.9,
  "output": 0.9
}
evrocnvidia/Llama-3.3-70B-Instruct-FP8128K$1.150$1.150· T ·
View
{
  "input": 1.15,
  "output": 1.15
}
Tinfoilllama3-3-70b128K$1.750$2.750· T ·
View
{
  "input": 1.75,
  "output": 2.75
}
Evidence

Published benchmark results

Artificial Analysis Coding Index vs top 8 models
GPT-5-Codex
38.9
Step 3.5 Flash 2603
34.6
North Mini Code
33.4
Gemini 2.5 Pro
32.0
Step 3.5 Flash
31.6
GLM-4.6
29.5
Qwen3 Max
26.4
Llama-3.3-70B-Instruct
10.7
SciCode vs top 8 models
Fugu
60.1
Fugu Ultra
58.7
Qwen3.7 Max
53.5
Gemini 2.5 Pro
42.8
GPT-5-Codex
40.9
Step 3.5 Flash
40.4
Gemini 2.5 Flash
39.4
Llama-3.3-70B-Instruct
26.0
Terminal-Bench Hard vs top 8 models
GPT-5-Codex
37.9
Step 3.5 Flash 2603
32.6
Step 3.5 Flash
27.3
Gemini 2.5 Pro
26.5
GLM-4.6
25.0
GLM-4.5
22.0
GLM-4.5-Air
20.5
Llama-3.3-70B-Instruct
3.0