# Llama 3.2 90B API Pricing

As of October 10, 2026, Llama 3.2 90B costs $0.72 per 1M input tokens and $0.72 per 1M output tokens on Vercel AI Gateway. It has a 128,000-token context window and returns up to 8,192 tokens per response.

- Page: https://models.litellm.ai/models/llama-3.2-90b
- Lab: Meta
- LiteLLM model name: `vercel_ai_gateway/meta/llama-3.2-90b`
- Context window: 128,000 tokens
- Max output: 8,192 tokens
- Added to LiteLLM: July 2025
- 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 |
|---|---|---|---|---|---|---|---|
| Vercel AI Gateway | `vercel_ai_gateway/meta/llama-3.2-90b` | $0.72 | $0.72 | – | – | – | 128K |

## Cost examples

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

- Vercel AI Gateway: $1.80

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

- Vercel AI Gateway: $7.344

## Features

Supported: Function calling, Image input.

## Use it with LiteLLM

```python
from litellm import completion

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

## FAQ

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

Llama 3.2 90B costs $0.72 per 1M input tokens and $0.72 per 1M output tokens on Vercel AI Gateway.

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

Llama 3.2 90B has a 128,000-token context window and returns up to 8,192 tokens per response.

### Which providers offer Llama 3.2 90B?

Llama 3.2 90B is available from Vercel AI Gateway through LiteLLM, using the model name vercel_ai_gateway/meta/llama-3.2-90b.

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

Use the LiteLLM Python SDK with model="vercel_ai_gateway/meta/llama-3.2-90b", 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 support?

Llama 3.2 90B supports function calling and image input.

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

Llama 3.2 90B was added to LiteLLM's model price file in July 2025.

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