Meta · Vision & multimodal
Llama 3.2 90B Vision Instruct
A cross-attention vision adapter bolted onto Llama 3.1 70B — capable at charts, documents and captioning, but image+text is English-only and it is superseded by Llama 4's native early fusion; pick it only when you need a 3.x-lineage vision model. Prices -1: weights only.
Open weights · Community or custom license · Data checked September 6, 2026 · Not a hands-on evaluation
Model ID meta-llama/Llama-3.2-90B-Vision-Instruct
- Parameters
- 90B90B (88.8B)
- Architecture
- Not recorded
- Context window
- 128,000 tokensMaximum input
- Max output
- Not recordedPer response
- Input price
- Not published
- Output price
- Not published
- Cached input
- Not published
- Blended price
- Not available3:1 input to output
- Knowledge cutoff
- 2023-12
- Released
- 2024-09-25
- Status
- ga
- Size band
- 40B to 120B
License and openness
Llama 3.2 90B Vision Instruct is released under the Llama 3.2 Community License Agreement. This is a community or custom license with its own conditions, which can include acceptable-use rules, user thresholds or naming requirements. Read it before commercial use. License terms can change between versions; confirm the text published with the weights you download.
Capabilities
| Input modalities | text, image |
|---|---|
| Output modalities | text |
What it is for
Prices -1: weights only.
Cost at list price
| Input | Not published |
|---|---|
| Output | Not published |
| Cached input | Not published |
| Blended, 3:1 | Not available |
The provider publishes no per-token price for this model. Any price you see elsewhere belongs to a third-party host, and running the weights yourself has hardware costs instead.
Estimate a workload across all models ↗Sources
- Source: github.com ↗
- Meta pricing ↗
- API docs ↗
- Full reference record for Llama 3.2 90B Vision Instruct ↗
- Meta in the reference ↗
Sources checked September 6, 2026. Specifications and prices change without notice; confirm against the provider before you commit.
Other open-weight models from Meta
- Muse Glimmer 30B · 30B dense
- Llama 4 Scout · 109B total · 17B active
- Llama 4 Maverick · 400B total · 17B active
- Llama 3.3 70B Instruct · 70B
- Llama 3.2 11B Vision Instruct · 11B
- Llama 3.2 3B Instruct · 3B
- Llama 3.2 1B Instruct · 1B
- Llama 3.1 405B Instruct · 405B
- Llama 3.1 70B Instruct · 70B
- Llama 3.1 8B Instruct · 8B