# Llama 3.3 8B Instruct API Pricing

Llama 3.3 8B Instruct is available through LiteLLM. It has a 128,000-token context window and returns up to 4,028 tokens per response.

- Page: https://models.litellm.ai/models/llama-3.3-8b-instruct
- Lab: Meta
- Context window: 128,000 tokens
- Max output: 4,028 tokens
- Added to LiteLLM: May 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 |
|---|---|---|---|---|---|---|---|
| Meta Llama API | `meta_llama/Llama-3.3-8B-Instruct` | – | – | – | – | – | 128K |

## Features

Supported: Function calling.

## FAQ

### What is the context window of Llama 3.3 8B Instruct?

Llama 3.3 8B Instruct has a 128,000-token context window and returns up to 4,028 tokens per response.

### What features does Llama 3.3 8B Instruct support?

Llama 3.3 8B Instruct supports function calling.

### When did LiteLLM add Llama 3.3 8B Instruct?

Llama 3.3 8B Instruct was added to LiteLLM's model price file in May 2025.

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