Skip to main content
Back to Explore

Llama 3.2 Instruct 90B (Vision)

Meta·Released 2024-09-25
Open SourceMultimodal

Pricing

Input

$1.38

per 1M tokens

Output

$1.38

per 1M tokens

Blended

$1.38

per 1M tokens

Cheaper than 31% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$1.38

Monthly

$41.40

vs. Similar Models

Solar MiniQ:0.0
$0.15-89%
Qwen2.5 TurboQ:+0.1
$0.09-94%
Reka Flash (Sep '24)Q:+0.1
$0.35-75%
Llama 3.1 Instruct 8BQ:-0.1
$0.10-93%

Performance

59

tokens/sec

Faster than 28% of models

0.64

seconds

Faster than 73% of models

0.64

seconds

Faster than 81% of models

Market Median

94 tok/s

37% slower

Median TTFT

1.10s

42% faster

Throughput/Dollar

43

tok/s per $/1M

Speed Comparison

Qwen: Qwen3 Max
59 tok/s-1%
Gemma 4 E4B (Non-reasoning)
60 tok/s+1%
Qwen3.6 27B (Non-reasoning)
59 tok/s-1%

Benchmarks

MMLU-Pro
67.1%
GPQA Diamond
43.2%
HLE
4.9%
LiveCodeBench
21.4%
SciCode
24.0%
TerminalBench HardNot evaluated
MATH-500
62.9%
AIME
5.0%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2Not evaluated
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models