Meta
Multimodal

Llama 3.2 90B Vision

Vision

Llama 3.2 with vision, Meta's first open-weights multimodal model at 90B.

Llama 3.2 90B Vision is a multimodal AI model from Meta. It costs $0.8800 per million input tokens and $0.8800 per million output tokens (blended $0.8800/M), with a 128,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.8800/M
per million input tokens
OUTPUT
$0.8800/M
per million output tokens
BLENDED 70/30
$0.8800/M
unchanged since 3 May
CONTEXT
128,000
tokens

Hand-maintained from Meta's published pricing; no check date on record.

What it is good at
  • Open-weights vision
  • 128K context
  • Wide hosted availability
Typical use cases
  • Self-hosted vision QA
  • Document understanding
  • Open-weights multimodal

Benchmarks

vs. best public score
MMLU86%
Multitask academic knowledge across 57 subjects. No source recorded yet.
MATH68%
High-school competition math problems. No source recorded yet.
LMArena Elo1239 Elo
Crowd-sourced head-to-head preference Elo rating. No source recorded yet.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

Also reported by the provider

Results on benchmarks outside the set we compare across models. They are listed for completeness and are deliberately excluded from the bars above and from every ranking on this site, because a score is only comparable against the same benchmark variant. Why benchmark scores do not compare →

  • GPQA Main (0-shot)46.7%self-reported by Meta · no date on the source · Maker evaluation details identify this as the GPQA main set, not Diamond, 0-shot. Not comparable with the GPQA Diamond column, so shown here and never ranked.

More from Meta

See all 20 →

Frequently asked questions

How much does Llama 3.2 90B Vision cost?

Llama 3.2 90B Vision costs $0.8800 per million input tokens and $0.8800 per million output tokens, for a blended reference rate of $0.8800 per million tokens.

What is Llama 3.2 90B Vision's context window?

Llama 3.2 90B Vision supports up to 128,000 tokens of context in a single request.

What is Llama 3.2 90B Vision best for?

Llama 3.2 90B Vision is well suited to Open-weights vision, 128K context and Wide hosted availability.

Who makes Llama 3.2 90B Vision?

Llama 3.2 90B Vision is developed and served by Meta. It was released in Sep 2024.

Terms used on this page