Skip to main content
Back to Explore

Llama 3.1 Instruct 8B

Meta·Released 2024-07-23
Open SourceMultimodal

Pricing

Input

$0.10

per 1M tokens

Output

$0.10

per 1M tokens

Blended

$0.10

per 1M tokens

Cheaper than 83% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.10

Monthly

$3.00

vs. Similar Models

Llama 3.2 Instruct 90B (Vision)Q:+0.1
$1.38+1280%
Solar MiniQ:+0.1
$0.15+50%
Qwen2.5 TurboQ:+0.2
$0.09-12%
Reka Flash (Sep '24)Q:+0.2
$0.35+250%

Performance

173

tokens/sec

Faster than 82% of models

0.51

seconds

Faster than 87% of models

0.51

seconds

Faster than 92% of models

Market Median

94 tok/s

85% faster

Median TTFT

1.10s

54% faster

Throughput/Dollar

1735

tok/s per $/1M

Speed Comparison

Qwen3 30B A3B 2507 Instruct
173 tok/s-0%
GPT-5.4 mini (medium)
175 tok/s+1%
OpenAI: GPT-5 Codex
177 tok/s+2%

Benchmarks

MMLU-Pro
47.6%
GPQA Diamond
25.9%
HLE
5.1%
LiveCodeBench
11.6%
SciCode
13.2%
TerminalBench Hard
0.8%
MATH-500
51.9%
AIME
7.7%
AIME 2025
4.3%
IFBench
28.6%
Long Context Recall
15.7%
Tau2
16.4%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models