Skip to main content
Back to Explore

Meta: Llama 3.3 70B Instruct

Meta·Released 2024-12-06
Open Source70B131K ctxllama3.3

About

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Pricing

Input

$0.10

per 1M tokens

Output

$0.32

per 1M tokens

Blended

$0.15

per 1M tokens

Cheaper than 74% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.15

Monthly

$4.65

vs. Similar Models

GLM-4.7-Flash (Non-reasoning)
$0.15-1%
Qwen: Qwen3 30B A3B Thinking 2507
$0.16+3%
MiMo-V2-Flash (Feb 2026)
$0.15-3%
MiMo-V2-Flash (Reasoning)
$0.15-3%

Performance

Context Window

131K

tokens

Larger than 27% of models

Max Output

16K

tokens

13% of context

Context Window Comparison

DeepSeek: DeepSeek V3.2
131KSame
OpenAI: gpt-oss-120b
131KSame
MoonshotAI: Kimi K2 0711
131KSame
llama3.370BGGUF / GPTQ / AWQ
Downloads

940.6K

Likes

2.8K

VRAM (FP16)

48-80 GB

GPU

A100 80GB

Quick Compare

Similar Models

Compare all 7 models

Used by Agents