# Llama 4 Maverick 17B 128e Instruct API Pricing

As of October 10, 2026, Llama 4 Maverick 17B 128e Instruct costs $0.35 per 1M input tokens and $1.15 per 1M output tokens from Google Vertex AI, the lowest of 9 providers. It has a 1,000,000-token context window and returns up to 1,000,000 tokens per response.

- Page: https://models.litellm.ai/models/llama-4-maverick-17b-128e-instruct
- Lab: Meta
- LiteLLM model name: `vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas`
- Context window: 1,000,000 tokens
- Max output: 1,000,000 tokens
- Added to LiteLLM: April 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 |
|---|---|---|---|---|---|---|---|
| Google Vertex AI | `vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas` | $0.35 | $1.15 | – | – | – | 1M |
| Meta Llama API (fp8) | `meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | – | – | – | – | – | 1M |
| SambaNova | `sambanova/Llama-4-Maverick-17B-128E-Instruct` | $0.63 | $1.80 | – | – | – | 128K |
| Azure AI Foundry (fp8) | `azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8` | $0.25 | $1.00 | – | – | – | 1M |
| DeepInfra (fp8) | `deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | $0.20 | $0.80 | – | – | – | 1M |
| IBM watsonx.ai (fp8) | `watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8` | $0.371 | $1.484 | – | – | – | 128K |
| Lambda (fp8) | `lambda_ai/llama-4-maverick-17b-128e-instruct-fp8` | $0.05 | $0.10 | – | – | – | 128K |
| Novita AI (fp8) | `novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8` | $0.27 | $0.85 | – | – | – | 1M |
| Oracle Cloud (OCI) (fp8) | `oci/meta.llama-4-maverick-17b-128e-instruct-fp8` | $0.72 | $0.72 | – | – | – | 1M |

## Cost examples

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

- Google Vertex AI: $1.275
- SambaNova: $2.16
- Google Vertex AI batch: $0.6375

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

- Google Vertex AI: $3.73
- SambaNova: $6.66

## Features

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

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Llama 4 Maverick 17B 128e Instruct cost?

Llama 4 Maverick 17B 128e Instruct costs $0.35 per 1M input tokens and $1.15 per 1M output tokens from Google Vertex AI, the lowest of 9 providers. Batch requests cost $0.175 per 1M input tokens and $0.575 per 1M output tokens.

### What is the context window of Llama 4 Maverick 17B 128e Instruct?

Llama 4 Maverick 17B 128e Instruct has a 1,000,000-token context window and returns up to 1,000,000 tokens per response.

### Which providers offer Llama 4 Maverick 17B 128e Instruct?

Llama 4 Maverick 17B 128e Instruct is available from 9 providers through LiteLLM: Google Vertex AI, Meta Llama API, SambaNova, Azure AI Foundry, DeepInfra, IBM watsonx.ai, Lambda, Novita AI and Oracle Cloud (OCI). The lowest price is on Google Vertex AI.

### How do I call Llama 4 Maverick 17B 128e Instruct with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="vertex_ai/meta/llama-4-maverick-17b-128e-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 Llama 4 Maverick 17B 128e Instruct support?

Llama 4 Maverick 17B 128e Instruct supports function calling, parallel tool calls, structured output and image input.

### When did LiteLLM add Llama 4 Maverick 17B 128e Instruct?

Llama 4 Maverick 17B 128e Instruct was added to LiteLLM's model price file in April 2025.

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