# Llama 3.3 70B Instruct API Pricing

As of October 10, 2026, Llama 3.3 70B Instruct costs $0.12 per 1M input tokens and $0.30 per 1M output tokens from Hyperbolic, the lowest of 18 providers. It has a 131,072-token context window and returns up to 131,072 tokens per response.

- Page: https://models.litellm.ai/models/llama-3.3-70b-instruct
- Lab: Meta
- LiteLLM model name: `hyperbolic/meta-llama/Llama-3.3-70B-Instruct`
- Context window: 131,072 tokens
- Max output: 131,072 tokens
- Added to LiteLLM: December 2024
- 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 |
|---|---|---|---|---|---|---|---|
| Hyperbolic | `hyperbolic/meta-llama/Llama-3.3-70B-Instruct` | $0.12 | $0.30 | – | – | – | 128K |
| Meta Llama API | `meta_llama/Llama-3.3-70B-Instruct` | – | – | – | – | – | 128K |
| Amazon Bedrock | `meta.llama3-3-70b-instruct-v1:0` | $0.72 | $0.72 | – | – | – | 128K |
| Azure AI Foundry | `azure_ai/Llama-3.3-70B-Instruct` | $0.71 | $0.71 | – | – | – | 128K |
| Crusoe | `crusoe/meta-llama/Llama-3.3-70B-Instruct` | $0.20 | $0.20 | – | – | – | 128K |
| DeepInfra | `deepinfra/meta-llama/Llama-3.3-70B-Instruct` | $0.23 | $0.40 | – | – | – | 128K |
| Google Vertex AI | `vertex_ai/meta/llama-3.3-70b-instruct-maas` | $0.72 | $0.72 | – | – | – | 128K |
| GradientAI | `gradient_ai/llama3.3-70b-instruct` | $0.65 | $0.65 | – | – | – | 128K |
| IBM watsonx.ai | `watsonx/meta-llama/llama-3-3-70b-instruct` | $0.7526 | $0.7526 | – | – | – | 128K |
| Nebius AI Studio | `nebius/meta-llama/Llama-3.3-70B-Instruct` | $0.13 | $0.40 | – | – | – | 128K |
| Novita AI | `novita/meta-llama/llama-3.3-70b-instruct` | $0.135 | $0.40 | – | – | – | 12K |
| Nscale | `nscale/meta-llama/Llama-3.3-70B-Instruct` | $0.20 | $0.20 | – | – | – | – |
| Oracle Cloud (OCI) | `oci/meta.llama-3.3-70b-instruct` | $0.72 | $0.72 | – | – | – | 128K |
| OVHcloud | `ovhcloud/Meta-Llama-3_3-70B-Instruct` | $0.67 | $0.67 | – | – | – | 131K |
| SambaNova | `sambanova/Meta-Llama-3.3-70B-Instruct` | $0.60 | $1.20 | – | – | – | 128K |
| Scaleway | `scaleway/meta/llama-3.3-70b-instruct` | $0.90 | $0.90 | – | – | – | 128K |
| Weights & Biases | `wandb/meta-llama/Llama-3.3-70B-Instruct` | $0.71 | $0.71 | – | – | – | 128K |
| Amazon Bedrock (US cross-region) | `us.meta.llama3-3-70b-instruct-v1:0` | $0.72 | $0.72 | – | – | – | 128K |
| Lambda (fp8) | `lambda_ai/llama3.3-70b-instruct-fp8` | $0.12 | $0.30 | – | – | – | 128K |

## Cost examples

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

- Hyperbolic: $0.39
- Nebius AI Studio: $0.46
- Novita AI: $0.47
- Crusoe: $0.50

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

- Hyperbolic: $1.26
- Nebius AI Studio: $1.38
- Novita AI: $1.43
- Crusoe: $2.04

## Features

Supported: Function calling, Parallel tool calls, Structured output.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="hyperbolic/meta-llama/Llama-3.3-70B-Instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

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

Llama 3.3 70B Instruct costs $0.12 per 1M input tokens and $0.30 per 1M output tokens from Hyperbolic, the lowest of 18 providers.

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

Llama 3.3 70B Instruct has a 131,072-token context window and returns up to 131,072 tokens per response.

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

Llama 3.3 70B Instruct is available from 18 providers through LiteLLM: Hyperbolic, Meta Llama API, Amazon Bedrock, Azure AI Foundry, Crusoe, DeepInfra, Google Vertex AI, GradientAI, IBM watsonx.ai, Nebius AI Studio, Novita AI and Nscale and 6 more. The lowest price is on Hyperbolic.

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

Use the LiteLLM Python SDK with model="hyperbolic/meta-llama/Llama-3.3-70B-Instruct", 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 support?

Llama 3.3 70B Instruct supports function calling, parallel tool calls and structured output.

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

Llama 3.3 70B Instruct was added to LiteLLM's model price file in December 2024.

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