# Llama 3.2 90B Vision Instruct API prices

Llama 3.2 90B Vision Instruct (llama) — 128k context, 8k max output.
1 metered per-token offers from 2 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| IO.NET | $0.35 | $0.4 | $0.175 | 16k |

## Summary

- Cheapest input: $0.35 per 1M tokens (IO.NET)
- Cheapest output: $0.4 per 1M tokens (IO.NET)
- First-party: not listed separately
- Free offers: Nvidia
- Subscription plans (not per-token): none
- Released: 2024-09-25
- Inputs: image, text

## FAQ

### What is the cheapest Llama 3.2 90B Vision Instruct API?

As of Oct 4, 2026, IO.NET has the lowest Llama 3.2 90B Vision Instruct output price at $0.4 per 1M tokens, and IO.NET has the lowest input price at $0.35 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Llama 3.2 90B Vision Instruct?

2 providers list Llama 3.2 90B Vision Instruct on Sovyron; 1 of them sell it at a metered per-token price.

### Is Llama 3.2 90B Vision Instruct free?

1 provider(s) list a free-tier offer: Nvidia. Free tiers usually have rate limits.

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

Llama 3.2 90B Vision Instruct supports a 128k-token context window and up to 8k output tokens.

HTML page: https://sovyron.com/models/llama-3-2-90b-vision-instruct/
Full dataset: https://sovyron.com/data/catalog.json