Llama 3.2 90B Vision

The largest multimodal Llama 3.2 at 90B parameters, adding image reasoning through cross-attention adapters on the Llama 3.1 70B backbone.

Params: 88.8B
Context: 128K tokens
Cutoff: Dec 2023
License: Llama 3.2 Community License

Visit Meta Compare vs other LLMs →

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving Llama 3.2 90B Vision, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Llama 3.2 90B Vision, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cost at 10M in + 2M out	Link
Meta Creator	Open weights, no hosted price			Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Llama 3.2 90B Vision needs about 56 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 4× RTX 4060 Ti at about $374 a month.

Single node ≤ 8

What it costs to self-host Llama 3.2 90B Vision at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 128K context)	Cost /mo
4-bit INT4 / FP4	56 GB72 GB	4× RTX 4060 Ti	$374$749
8-bit FP8 / INT8	96 GB112 GB	8× RTX 4060 Ti	$749$749
16-bit FP16 / BF16	190 GB222 GB	8× RTX A6000	$3,283$3,283

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.

Salad

Access 60,000+ daily active GPUs across 191 countries, from $0.02/hour

Run RTX 50-series and 40-series cards without datacenter pricing

Pick a priority level to balance cost against interruptions

Per-second billing, with no charge for cold starts or image pulls

View Pricing

Capabilities

What Llama 3.2 90B Vision accepts and can do, as published by Meta.

Text Accepts and generates natural-language text.
Image Accepts images as input alongside text.
Function calling Connect to external tools, APIs, and systems.

Common questions

What is Llama 3.2 90B Vision good for?

Image reasoning with text, at the heavy end of the Llama 3.2 family. Open weights under the Llama 3.2 Community License, servable on a single high-memory GPU.

When is Llama 3.2 90B Vision not a good fit?

Tool calling on image inputs: it works only with text-only prompts. Its knowledge is older than the current open models', and self-hosting takes a high-memory GPU rather than a consumer card.

What is the cheapest way to run Llama 3.2 90B Vision?

No provider we track hosts it; self-hosting on the cheapest rental that fits (4x RTX 4060 Ti, $0.52 per hour) costs about $374 a month.

Can I self-host Llama 3.2 90B Vision?

Yes. The weights are released under the Llama 3.2 Community License. At 4-bit it needs about 56 GB of GPU memory, which starts at roughly $374 a month on the cheapest rental that fits.