# Llama3.3 70B API Pricing

As of October 10, 2026, Llama3.3 70B costs $0.72 per 1M input tokens and $0.72 per 1M output tokens from Snowflake Cortex, the lowest of 3 providers. It has a 128,000-token context window and returns up to 16,384 tokens per response.

- Page: https://models.litellm.ai/models/llama-3.3-70b
- Lab: Meta
- LiteLLM model name: `snowflake/llama3.3-70b`
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Added to LiteLLM: February 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/llama3.3-70b` | $0.72 | $0.72 | – | – | – | 128K |
| Cerebras | `cerebras/llama-3.3-70b` | $0.85 | $1.20 | – | – | – | 128K |
| Snowflake Cortex | `snowflake/snowflake-llama-3.3-70b` | $0.72 | $0.72 | – | – | – | 128K |
| Vercel AI Gateway | `vercel_ai_gateway/meta/llama-3.3-70b` | $0.72 | $0.72 | – | – | – | 128K |

## Cost examples

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

- Snowflake Cortex: $1.80
- Vercel AI Gateway: $1.80
- Cerebras: $2.30

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

- Snowflake Cortex: $7.344
- Vercel AI Gateway: $7.344
- Cerebras: $8.74

## Features

Supported: Function calling.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="snowflake/llama3.3-70b",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Llama3.3 70B cost?

Llama3.3 70B costs $0.72 per 1M input tokens and $0.72 per 1M output tokens from Snowflake Cortex, the lowest of 3 providers.

### What is the context window of Llama3.3 70B?

Llama3.3 70B has a 128,000-token context window and returns up to 16,384 tokens per response.

### Which providers offer Llama3.3 70B?

Llama3.3 70B is available from 3 providers through LiteLLM: Snowflake Cortex, Cerebras and Vercel AI Gateway. The lowest price is on Snowflake Cortex.

### How do I call Llama3.3 70B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="snowflake/llama3.3-70b", 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 Llama3.3 70B support?

Llama3.3 70B supports function calling.

### When did LiteLLM add Llama3.3 70B?

Llama3.3 70B was added to LiteLLM's model price file in February 2025.

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