# Llama3.1 405B API Pricing

As of October 10, 2026, Llama3.1 405B costs $1.20 per 1M input tokens and $1.20 per 1M output tokens on Snowflake Cortex. It has a 128,000-token context window and returns up to 16,384 tokens per response.

- Page: https://models.litellm.ai/models/llama-3.1-405b
- Lab: Meta
- LiteLLM model name: `snowflake/llama3.1-405b`
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Added to LiteLLM: March 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 |
|---|---|---|---|---|---|---|---|
| Snowflake Cortex | `snowflake/llama3.1-405b` | $1.20 | $1.20 | – | – | – | 128K |
| Snowflake Cortex | `snowflake/snowflake-llama-3.1-405b` | – | – | – | – | – | 8K |

## Cost examples

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

- Snowflake Cortex: $3.00

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

- Snowflake Cortex: $12.24

## Features

Supported: Function calling.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="snowflake/llama3.1-405b",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Llama3.1 405B cost?

Llama3.1 405B costs $1.20 per 1M input tokens and $1.20 per 1M output tokens on Snowflake Cortex.

### What is the context window of Llama3.1 405B?

Llama3.1 405B has a 128,000-token context window and returns up to 16,384 tokens per response.

### Which providers offer Llama3.1 405B?

Llama3.1 405B is available from Snowflake Cortex through LiteLLM, using the model name snowflake/llama3.1-405b.

### How do I call Llama3.1 405B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="snowflake/llama3.1-405b", 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 Llama3.1 405B support?

Llama3.1 405B supports function calling.

### When did LiteLLM add Llama3.1 405B?

Llama3.1 405B was added to LiteLLM's model price file in March 2025.

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