CtrlAltDebrief
Deprecated on Jun 13, 2026. 4 providers still list it at the prices below.

Llama 3.2 90B Vision InstructDeprecated

MetaFirst listed Sep 2024
VisionTool useStructured output
Compare Llama 3.2 90B Vision InstructCount tokens for Llama 3.2 90B Vision Instruct
Context
131K
Max output
128K
Serving providers
4
Cheapest input
$0.90 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices
Intelligence Index
6.4
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
EvalComputeProxyFrozen Aug 18, 202621.7default—
GPQA Diamond43%default—
Humanity's Last Exam4%default—
LiveCodeBenchArtificial Analysis did not report this score in its latest run on Oct 14, 202621%——
MMLU-ProFrozen Aug 18, 202667%default—
MMMU-Pro39%default—
SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 202624%——
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $0.90 to $2.04 per 1M tokens across 4 providers, so the dearest route costs 127% more than the cheapest for the same model.

Serving providerInput /1MOutput /1MEndpoints
Fireworks AICheapest$0.90$0.901
Standardfireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct
ComponentUnitStandard
Text input/1M tok$0.90
Text output/1M tok$0.90
OCI$2.00$2.001
Watsonx$2.00$2.001
Azure$2.04$2.041

Price history

listed seller prices, input and output per 1M tokens
Input Output
Input down 61% since first tracked
$0.00$0.50$1.00Sep 26Aug 7Aug 22Jun 22$0.40$0.35

Cost calculator

estimate your monthly spend on this model
$252
estimated / month

Model IDs

copy the exact identifier for your platform
fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instructwatsonx/meta-llama/llama-3-2-90b-vision-instructoci/meta.llama-3.2-90b-vision-instructazure_ai/Llama-3.2-90B-Vision-Instruct

Frequently asked questions

Llama 3.2 90B Vision Instruct pricing, context and availability

Is Llama 3.2 90B Vision Instruct still available?

Llama 3.2 90B Vision Instruct was deprecated on 2026-06-13, but 4 serving providers still list it.

How much does Llama 3.2 90B Vision Instruct cost?

Llama 3.2 90B Vision Instruct costs $0.90 per 1M input tokens from Fireworks AI, and $0.90 per 1M output tokens from Fireworks AI. Across 4 serving providers, input prices range from $0.90 to $2.04 per 1M tokens.

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

Llama 3.2 90B Vision Instruct accepts up to 131K tokens of context and can return up to 128K output tokens.

Which providers serve Llama 3.2 90B Vision Instruct?

Llama 3.2 90B Vision Instruct is available from 4 serving providers, each with its own pricing and model ID. Fireworks AI is currently the cheapest.

What can Llama 3.2 90B Vision Instruct do?

Llama 3.2 90B Vision Instruct supports image input (vision), tool use and structured output.

Other Meta models

compare pricing across the Meta lineup
Llama 3.3 70B Instruct$0.12/1M · 18 providersLlama 3.1 8B Instruct$0.02/1M · 17 providersLlama 3.1 70B Instruct$0.12/1M · 12 providersLlama 3.2 3B Instruct$0.015/1M · 11 providersLlama 4 Scout 17B 16e Instruct$0.05/1M · 11 providersLlama 3.1 405B Instruct$0.12/1M · 9 providersLlama 3 70B Instruct$0.12/1M · 9 providersLlama 3.2 1B Instruct$0.02/1M · 8 providers
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI