LLM Reference

Llama 3.2 90B Vision

Released
2024-09-25
Last refreshed
2026-07-09
Status
Researched 90d ago
Open weightsCommercial use: conditionalRAGLong contextVisionClassificationJSON / Tool use

Llama 3.2 90B Vision is worth evaluating for rag, long context, and vision when its provider route and context window match the workload.

Use it for

  • Teams evaluating rag, long context, and vision
  • Workloads that can use a 128k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Llama 3.2
Released
2024-09-25
Context
128k
Parameters
88.8B
Architecture
Decoder Only
Knowledge cutoff
2024-03
Specialization
general
Openness
Open weights
License
Llama 3 CommunityCommercial use: conditional
Weights
Unknown
Code
Unknown
Training
Fine-tuned
Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website
Pricing
Output / 1M
$1.80
Input / 1M
$1.35

Cheapest of 1 route · AWS Bedrock

About

Advanced multimodal model with image reasoning, visual question answering, and document analysis

Llama 3.2 90B Vision is an open-weight model in the Llama 3.2 family. The structured metadata tracks a 128k-token context window, vision, and structured outputs. This page tracks provider routes through AWS Bedrock, with the cheapest tracked route listed at $1.35 input and $1.8 output per 1M tokens. Headline tracked benchmarks include Massive Multi-discipline Multimodal Understanding 60.3 and MMMU Pro 45.2.

Top use-case fit

RAG

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Vision

Q/$ C

1 relevant benchmark in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
AWS Bedrock$1.35$1.80
Serverless

Available via routers & gateways(1)

Capabilities

VisionStructured Outputs

Benchmark peer barsfor Vision

Benchmark scores(2)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
Massive Multi-discipline Multimodal Understanding60.3Observed 2026-04-15Source
MMMU Pro45.2LLM-Stats aggregatorObserved 2026-06-07Source

Migration checks

No linked migration route is available for this model yet.

Compare Llama 3.2 90B Vision with other models

Frequently asked questions

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

Llama 3.2 90B Vision has a context window of 128k tokens.

How much does Llama 3.2 90B Vision cost?

Llama 3.2 90B Vision is available at $1.35/1M input tokens through AWS Bedrock.

When was Llama 3.2 90B Vision released?

Llama 3.2 90B Vision was released on 2024-09-25.

Which providers offer Llama 3.2 90B Vision?

Llama 3.2 90B Vision is available from 1 provider: AWS Bedrock.

What benchmarks has Llama 3.2 90B Vision been tested on?

Llama 3.2 90B Vision has been evaluated on 2 benchmarks, including Massive Multi-discipline Multimodal Understanding, MMMU Pro.