AI Model Watch
Models / Meta

Llama 3.2 90B Vision Instruct

GA

Open-weight multimodal (text+image), ~88.8B params, 128k context. License: Llama 3.2 Community License. Source is the 3.2 11B Vision card which documents the 90B sibling (same architecture/128k ctx/Dec-2023 cutoff). Image+text tasks are English-primary; text-only adds German, French, Italian, Portuguese, Hindi, Spanish, Thai. Per-token hosted price not separately captured this pass (null). Dedicated card: huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct.

Llama 3.2 90B Vision Instruct by Meta is tracked live in our LLM catalog, with a 128K (128.000-token) context window. It is generally available (GA), with a knowledge cutoff of Dec 2023. Its weights are publicly downloadable, so it can be self-hosted on your own infrastructure.

Last verified: 13 Aug 2026 · sourced from official provider documentation

Provider
Meta
Status
GA
Input price
—
Output price
—
Cached input
—
Blended price
—
Context window
128.000 tokens (128K)
Max output
—
Modality
text, image
Open weights
Yes — self-hostable
Knowledge cutoff
2023-12
Released
25 Sep 2024
API string
meta-llama/Llama-3.2-90B-Vision-Instruct

Source: Meta official documentation ↗

See also

Explore more

All Meta models→

Prices, context windows and lifecycle status for every Meta model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

Llama 3.2 90B Vision Instruct — questions & answers

What is the context window of Llama 3.2 90B Vision Instruct?

Llama 3.2 90B Vision Instruct has a 128.000-token context window (128K).

Is Llama 3.2 90B Vision Instruct deprecated?

No — Llama 3.2 90B Vision Instruct is generally available (GA) and not currently scheduled for deprecation or retirement in our tracker.

Does Llama 3.2 90B Vision Instruct support image or vision input?

Yes — Llama 3.2 90B Vision Instruct accepts image input. Listed modalities: text, image.

Can I self-host Llama 3.2 90B Vision Instruct?

Yes — Llama 3.2 90B Vision Instruct is an open-weight model: its weights are publicly downloadable, so you can run it on your own infrastructure (subject to its license) instead of only calling Meta's API.

What is the API model string for Llama 3.2 90B Vision Instruct?

The API model identifier for Llama 3.2 90B Vision Instruct is "meta-llama/Llama-3.2-90B-Vision-Instruct" when calling Meta's API.

What is Llama 3.2 90B Vision Instruct's knowledge cutoff?

Llama 3.2 90B Vision Instruct's training knowledge cutoff is Dec 2023.