Meta › Llama 3.2 90B Vision Instruct › Pricing

Llama 3.2 90B Vision Instruct pricing

Cheapest host: DeepInfra · checked Oct 23, 2026
Benchmarks and alternatives →
$0.35 / $0.40per 1M tokens in / out

Price sheetper 1M tokens

Input$0.35DeepInfra
Output$0.40
Context33Ktokens

Where to buy1 provider · per 1M tokens

ProviderInputOutputContext
DeepInfra$0.35$0.40—

In Meta's line-upper 1M in / out

Meta Llama 3 70B Instruct$0.30 / $0.40−10%
Llama 3.2 11B Vision Instruct$0.34 / $0.34−5%
Llama 4 Maverick 17B 128E Instruct FP8$0.20 / $0.80−3%
Llama 3.2 90B Vision Instruct$0.35 / $0.40this model
Llama 3 8B$0.30 / $0.60+3%
Llama 3.1 70B Instruct$0.40 / $0.40+10%
Muse Glimmer 30B$0.30 / $1.10+38%
<
All Llama API prices →

Cheaper for the same workvs Llama 3.2 90B Vision Instruct

GLM 5.3 Flash unstatedOpen-34%score wins 84%$0.15 / $0.50
Gemma 4 31B unstatedOpen-56%score wins 83%$0.10 / $0.34
Gemma 4 26B A4B unstatedOpen-28%score wins 82%$0.15 / $0.60
MiMo v2.6 Flash unstatedOpen-52%score wins 81%$0.14 / $0.28
MiMo v2.5 unstatedOpen-52%score wins 81%$0.14 / $0.28
All alternatives and what breaks when you switch →

Pricing questions

How much does Llama 3.2 90B Vision Instruct cost?›

$0.35 per 1M input tokens and $0.40 per 1M output tokens.

Is Llama 3.2 90B Vision Instruct free to use?›

There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.

What is a cheaper alternative to Llama 3.2 90B Vision Instruct?›

GLM 5.3 Flash at unstated effort costs -34% per task with a score wins 84% on GPQA Diamond · Epoch.