# Llama 3.2 90B Vision Instruct API Pricing

As of October 10, 2026, Llama 3.2 90B Vision Instruct is free to use from Google Vertex AI, the lowest of 3 providers. It has a 128,000-token context window and returns up to 2,048 tokens per response.

- Page: https://models.litellm.ai/models/llama-3.2-90b-vision-instruct
- Lab: Meta
- LiteLLM model name: `vertex_ai/meta/llama-3.2-90b-vision-instruct-maas`
- Context window: 128,000 tokens
- Max output: 2,048 tokens
- Added to LiteLLM: October 2024
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Google Vertex AI | `vertex_ai/meta/llama-3.2-90b-vision-instruct-maas` | $0 | $0 | – | – | – | 128K |
| IBM watsonx.ai | `watsonx/meta-llama/llama-3-2-90b-vision-instruct` | $2.00 | $2.00 | – | – | – | 128K |
| Oracle Cloud (OCI) | `oci/meta.llama-3.2-90b-vision-instruct` | $2.00 | $2.00 | – | – | – | 128K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Google Vertex AI: $0
- IBM watsonx.ai: $5.00
- Oracle Cloud (OCI): $5.00

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Google Vertex AI: $0
- IBM watsonx.ai: $20.40
- Oracle Cloud (OCI): $20.40

## Features

Supported: Function calling, Parallel tool calls, Image input.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="vertex_ai/meta/llama-3.2-90b-vision-instruct-maas",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

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

Llama 3.2 90B Vision Instruct is free to use from Google Vertex AI, the lowest of 3 providers.

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

Llama 3.2 90B Vision Instruct has a 128,000-token context window and returns up to 2,048 tokens per response.

### Which providers offer Llama 3.2 90B Vision Instruct?

Llama 3.2 90B Vision Instruct is available from 3 providers through LiteLLM: Google Vertex AI, IBM watsonx.ai and Oracle Cloud (OCI). The lowest price is on Google Vertex AI.

### How do I call Llama 3.2 90B Vision Instruct with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="vertex_ai/meta/llama-3.2-90b-vision-instruct-maas", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does Llama 3.2 90B Vision Instruct support?

Llama 3.2 90B Vision Instruct supports function calling, parallel tool calls and image input.

### When did LiteLLM add Llama 3.2 90B Vision Instruct?

Llama 3.2 90B Vision Instruct was added to LiteLLM's model price file in October 2024.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json