# Llama 2 7B API Pricing

As of October 10, 2026, Llama 2 7B costs $0.05 per 1M input tokens and $0.25 per 1M output tokens on Replicate. It has a 4,096-token context window and returns up to 4,096 tokens per response.

- Page: https://models.litellm.ai/models/llama-2-7b
- Lab: Meta
- LiteLLM model name: `replicate/meta/llama-2-7b`
- Context window: 4,096 tokens
- Max output: 4,096 tokens
- Added to LiteLLM: May 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 |
|---|---|---|---|---|---|---|---|
| Replicate | `replicate/meta/llama-2-7b` | $0.05 | $0.25 | – | – | – | 4K |

## Cost examples

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

- Replicate: $0.225

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="replicate/meta/llama-2-7b",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Llama 2 7B cost?

Llama 2 7B costs $0.05 per 1M input tokens and $0.25 per 1M output tokens on Replicate.

### What is the context window of Llama 2 7B?

Llama 2 7B has a 4,096-token context window and returns up to 4,096 tokens per response.

### Which providers offer Llama 2 7B?

Llama 2 7B is available from Replicate through LiteLLM, using the model name replicate/meta/llama-2-7b.

### How do I call Llama 2 7B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="replicate/meta/llama-2-7b", 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 2 7B?

Llama 2 7B was added to LiteLLM's model price file in May 2024.

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