# Llama 3.3 70B Instruct FP8 Dynamic API Pricing

As of October 10, 2026, Llama 3.3 70B Instruct FP8 Dynamic costs $0.72 per 1M input tokens and $0.72 per 1M output tokens on Oracle Cloud (OCI). It has a 128,000-token context window and returns up to 4,000 tokens per response.

- Page: https://models.litellm.ai/models/llama-3.3-70b-instruct-fp8-dynamic
- Lab: Meta
- LiteLLM model name: `oci/meta.llama-3.3-70b-instruct-fp8-dynamic`
- Context window: 128,000 tokens
- Max output: 4,000 tokens
- Added to LiteLLM: April 2026
- 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 |
|---|---|---|---|---|---|---|---|
| Oracle Cloud (OCI) | `oci/meta.llama-3.3-70b-instruct-fp8-dynamic` | $0.72 | $0.72 | – | – | – | 128K |

## Cost examples

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

- Oracle Cloud (OCI): $1.80

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

- Oracle Cloud (OCI): $7.344

## Features

Supported: Function calling.
Not supported: Structured output.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="oci/meta.llama-3.3-70b-instruct-fp8-dynamic",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Llama 3.3 70B Instruct FP8 Dynamic cost?

Llama 3.3 70B Instruct FP8 Dynamic costs $0.72 per 1M input tokens and $0.72 per 1M output tokens on Oracle Cloud (OCI).

### What is the context window of Llama 3.3 70B Instruct FP8 Dynamic?

Llama 3.3 70B Instruct FP8 Dynamic has a 128,000-token context window and returns up to 4,000 tokens per response.

### Which providers offer Llama 3.3 70B Instruct FP8 Dynamic?

Llama 3.3 70B Instruct FP8 Dynamic is available from Oracle Cloud (OCI) through LiteLLM, using the model name oci/meta.llama-3.3-70b-instruct-fp8-dynamic.

### How do I call Llama 3.3 70B Instruct FP8 Dynamic with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="oci/meta.llama-3.3-70b-instruct-fp8-dynamic", 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 3.3 70B Instruct FP8 Dynamic support?

Llama 3.3 70B Instruct FP8 Dynamic supports function calling. It does not support structured output.

### When did LiteLLM add Llama 3.3 70B Instruct FP8 Dynamic?

Llama 3.3 70B Instruct FP8 Dynamic was added to LiteLLM's model price file in April 2026.

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