Azure

Llama-3.2-90B-Vision-Instruct

Name: Llama-3.2-90B-Vision-Instruct
Brand: Azure

Canonical ID: azure/llama-3.2-90b-vision-instruct

More Azure models More llama-3.2-90b-vision-instruct family models

Llama-3.2-90B-Vision-Instruct is listed under Azure in LLM Directory with pricing, context limits, modalities, and capability metadata for quick comparison.

Reasoning: No Tool use: Yes

Overview

text image

Provider: Azure
Family: llama-3.2-90b-vision-instruct
Release date: 2024-09-25
Last updated: 2024-09-25
Input modalities: text, image
Output modalities: text

Pricing and Limits

Token pricing

Input: $2.04/1M
Output: $2.04/1M
Cached input: N/A

Context and output

Context window: 128,000
Max output tokens: 8,192
Qualified ID: azure/llama-3.2-90b-vision-instruct

Model Summary

Llama-3.2-90B-Vision-Instruct is a model listing in the Azure provider catalog. It is categorized under the llama-3.2-90b-vision-instruct family.

The model supports text, image modalities across input/output paths. Reported context capacity is 128,000. Pricing is listed at $2.04/1M input and $2.04/1M output.

Same Family: llama-3.2-90b-vision-instruct

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output	Flags
Llama 3.2 90B Vision Instruct io_net/meta-llama/Llama-3.2-90B-Vision-Instruct	IO.NET	16,000	$0.35/1M	$0.4/1M	Tools
Llama-3.2-90B-Vision-Instruct azure_cognitive_services/llama-3.2-90b-vision-instruct	Azure Cognitive Services	128,000	$2.04/1M	$2.04/1M	Tools
Llama-3.2-90B-Vision-Instruct github_models/meta/llama-3.2-90b-vision-instruct	GitHub Models	128,000	$0/1M	$0/1M	Reasoning Tools

Llama-3.2-90B-Vision-Instruct

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From Azure

Claude Fable 5

Claude Fable 5.1

Claude Haiku 4.5

Claude Haiku 5.5

Claude Mythos 5

Claude Opus 4.1

Claude Opus 4.5

Claude Opus 4.6

Same Family: llama-3.2-90b-vision-instruct