Skip to main content
Back to Explore

Llama 3.1 Instruct 405B

Meta·Released 2024-07-23
Open SourceMultimodal

Pricing

Input

$2.75

per 1M tokens

Output

$6.50

per 1M tokens

Blended

$3.69

per 1M tokens

Cheaper than 15% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$3.69

Monthly

$110.64

vs. Similar Models

Llama 3.3 Instruct 70BQ:+0.1
$0.61-83%
Mistral Small 3.1Q:+0.1
$0.14-96%
OpenAI: GPT-4o (2024-05-13)Q:+0.1
$7.50+103%
Qwen3 32B (Non-reasoning)Q:+0.1
$0.26-93%

Performance

82

tokens/sec

Faster than 41% of models

0.72

seconds

Faster than 69% of models

0.72

seconds

Faster than 78% of models

Market Median

94 tok/s

13% slower

Median TTFT

1.11s

35% faster

Throughput/Dollar

22

tok/s per $/1M

Speed Comparison

Mistral 7B Instruct
82 tok/s+0%
OpenAI: GPT-5.5
82 tok/s-1%
Ministral 3 8B
83 tok/s+1%

Benchmarks

MMLU-Pro
73.2%
GPQA Diamond
51.5%
HLE
4.2%
LiveCodeBench
30.5%
SciCode
29.9%
TerminalBench Hard
6.8%
MATH-500
70.3%
AIME
21.3%
AIME 2025
3.0%
IFBench
39.0%
Long Context Recall
24.3%
Tau2
19.0%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models