Llama 3.2 Instruct (90B)
The 90B model of the Llama 3.2-Vision collection of pretrained and instruction-tuned multimodal image reasoning models, for visual question answering, document understanding, image captioning, visual grounding, and assistant-like chat with images.
text + image → text · made by Meta
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | standard | $0.72per Mtok in$0.72per Mtok outaws.amazon.com · read 2026-08-24 |
| AWS Bedrock cloud | in-region | $0.72per Mtok in$0.72per Mtok outpricing.us-east-1.amazonaws.com · read 2026-08-24 |
Measured 1 standing
| Place | Board | Metric | Score |
|---|---|---|---|
| 256thof 302 | Artificial Analysis · Intelligence Index | Artificial Analysis Intelligence Index | 6 |
About
Llama 3.2 Instruct (90B) — a text model from Meta, sold by one company from $0.72 in and $0.72 out per million tokens, placed 256th of 302 on Artificial Analysis · Intelligence Index.
It takes text and images and returns text, with a context window of 128,000 tokens. The catalogue files it under ocr and search. Only AWS Bedrock sells it, at $0.72 in and $0.72 out per million tokens. Beside the standard rate there is a regional lane. It stands 256th of 302 on Artificial Analysis · Intelligence Index.
Every current figure
- Maker
- Meta
- Register
- model
- Takes
- text + image
- Returns
- text
- Context
- 128,000 tokens
- Parameters
- 90 billion · read from its own name
- Sellers
- 1
- Maker's own price
- not read
- Price
- $0.72 in and $0.72 out per million tokens — AWS Bedrock
- Boards
- 1
- Best place
- 256th of 302 — Artificial Analysis · Intelligence Index
Known as 2 names
Llama 3.2 90Bmeta.llama3-2-90b-instruct-v1:0