# Llama3 70B Instruct API Pricing

As of October 10, 2026, Llama3 70B Instruct is free to use from Google Vertex AI, the lowest of 7 providers. It has a 32,000-token context window and returns up to 32,000 tokens per response.

- Page: https://models.litellm.ai/models/llama3-70b-instruct
- Lab: Meta
- LiteLLM model name: `vertex_ai/meta/llama3-70b-instruct-maas`
- Context window: 32,000 tokens
- Max output: 32,000 tokens
- Added to LiteLLM: April 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 |
|---|---|---|---|---|---|---|---|
| Google Vertex AI | `vertex_ai/meta/llama3-70b-instruct-maas` | $0 | $0 | – | – | – | 32K |
| Amazon Bedrock | `meta.llama3-70b-instruct-v1:0` | $2.65 | $3.50 | – | – | – | 8K |
| Anyscale | `anyscale/meta-llama/Meta-Llama-3-70B-Instruct` | $1.00 | $1.00 | – | – | – | 8K |
| Azure AI Foundry | `azure_ai/Meta-Llama-3-70B-Instruct` | $1.10 | $0.37 | – | – | – | 8K |
| Hyperbolic † | `hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct` | $0.12 | $0.30 | – | – | – | 128K |
| Novita AI | `novita/meta-llama/llama-3-70b-instruct` | $0.51 | $0.74 | – | – | – | 8K |
| Replicate | `replicate/meta/llama-3-70b-instruct` | $0.65 | $2.75 | – | – | – | 8K |
| Amazon Bedrock (ap-south-1) | `bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0` | $3.18 | $4.20 | – | – | – | 8K |
| Amazon Bedrock (ca-central-1) | `bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0` | $3.05 | $4.03 | – | – | – | 8K |
| Amazon Bedrock (eu-west-1) | `bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0` | $2.86 | $3.78 | – | – | – | 8K |
| Amazon Bedrock (eu-west-2) | `bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0` | $3.45 | $4.55 | – | – | – | 8K |
| Amazon Bedrock (sa-east-1) | `bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0` | $4.45 | $5.88 | – | – | – | 8K |
| Amazon Bedrock (us-east-1) | `bedrock/us-east-1/meta.llama3-70b-instruct-v1:0` | $2.65 | $3.50 | – | – | – | 8K |
| Amazon Bedrock (us-gov-east-1) | `bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0` | $2.65 | $3.50 | – | – | – | 8K |
| Amazon Bedrock (us-gov-west-1) | `bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0` | $2.65 | $3.50 | – | – | – | 8K |
| Amazon Bedrock (us-west-1) | `bedrock/us-west-1/meta.llama3-70b-instruct-v1:0` | $2.65 | $3.50 | – | – | – | 8K |

† Differs from other providers by more than 8x; check the provider's pricing page.

## Cost examples

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

- Google Vertex AI: $0
- Novita AI: $1.39
- Replicate: $2.675
- Anyscale: $2.50

## Features

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

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="vertex_ai/meta/llama3-70b-instruct-maas",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Llama3 70B Instruct cost?

Llama3 70B Instruct is free to use from Google Vertex AI, the lowest of 7 providers.

### What is the context window of Llama3 70B Instruct?

Llama3 70B Instruct has a 32,000-token context window and returns up to 32,000 tokens per response.

### Which providers offer Llama3 70B Instruct?

Llama3 70B Instruct is available from 7 providers through LiteLLM: Google Vertex AI, Amazon Bedrock, Anyscale, Azure AI Foundry, Hyperbolic, Novita AI and Replicate. The lowest price is on Google Vertex AI.

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

Use the LiteLLM Python SDK with model="vertex_ai/meta/llama3-70b-instruct-maas", 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 70B Instruct support?

Llama3 70B Instruct supports function calling, parallel tool calls, structured output and PDF input.

### When did LiteLLM add Llama3 70B Instruct?

Llama3 70B Instruct was added to LiteLLM's model price file in April 2024.

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