# Llama 3 70B Instruct Turbo API Pricing

As of October 10, 2026, Llama 3 70B Instruct Turbo costs $0.88 per 1M input tokens and $0.88 per 1M output tokens on Together AI. It has an 8,192-token context window.

- Page: https://models.litellm.ai/models/llama-3-70b-instruct-turbo
- Lab: Meta
- LiteLLM model name: `together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo`
- Context window: 8,192 tokens
- Added to LiteLLM: September 14, 2026
- Deprecation date: December 23, 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 |
|---|---|---|---|---|---|---|---|
| Together AI | `together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo` | $0.88 | $0.88 | – | – | – | 8K |

## Cost examples

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

- Together AI: $2.20

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Llama 3 70B Instruct Turbo cost?

Llama 3 70B Instruct Turbo costs $0.88 per 1M input tokens and $0.88 per 1M output tokens on Together AI.

### What is the context window of Llama 3 70B Instruct Turbo?

Llama 3 70B Instruct Turbo has an 8,192-token context window.

### Which providers offer Llama 3 70B Instruct Turbo?

Llama 3 70B Instruct Turbo is available from Together AI through LiteLLM, using the model name together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo.

### How do I call Llama 3 70B Instruct Turbo with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo", 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.

### When did LiteLLM add Llama 3 70B Instruct Turbo?

Llama 3 70B Instruct Turbo was added to LiteLLM's model price file on September 14, 2026.

### Is Llama 3 70B Instruct Turbo being deprecated?

Together AI deprecated together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo on December 23, 2025.

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