LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Llama-3.2-90B-Vision-Instruct

meta·meta/llama-3.2-90b-vision-instruct·GA·Open weights·llama series
Large open multimodal Llama model for image reasoning, document QA, and captioning

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·IO.NETCloud
$0.35 / $0.40
Blended $0.36
1 more $0 channels
Context
16,000
Output limit
4,096
Knowledge cutoff
2023-12
Released / updated
2024-09-25 / 2024-09-25
Capabilities
Reasoning✓ Tool use? Structured output✓ Temperature✓ Attachments
Modalities
TextImage
License
Llama 3.2 Community License
Weights
Hugging Face

Available at 2 providers1 with public prices · 1 free

  • ProviderInput / Output
  • NvidiaCloud
    Free
    Context 128,000 ⚠Output limit 8,192
  • IO.NETCloud
    meta-llama/Llama-3.2-90B-Vision-Instruct
    $0.35 / $0.40
    Cache read $0.18Context 16,000Output limit 4,096deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NvidiaCloudFree——128,000 ⚠8,192
IO.NET
meta-llama/Llama-3.2-90B-Vision-Instruct
Cloud$0.35$0.40$0.18$0.7016,0004,096deprecated

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1IO.NET$69.00

1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.36

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-05). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

Omega Directive 24B Unslop v2.0same series—EVA-LLaMA-3.33-70B-v0.1same series—Llama 3.3 70B Instruct abliteratedsame series—
Data partly from models.dev (MIT)