How much does the Llama 4 Maverick API cost?

On FastMetal, Llama 4 Maverick is billed per token: $0.22 per 1M input tokens and $0.88 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Llama 4 Maverick with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "llama-4-maverick" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Llama 4 Maverick?

1,048,576 tokens, shared between the prompt and the response.

What do I need to try Llama 4 Maverick?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Back to Models

Llama 4 Maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction. Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.

4/5/2025

1,048,576 tokens

Input: $0.22/M

Output: $0.88/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

Output

text

Supported Parameters

frequency_penalty

logit_bias

max_tokens

min_p

presence_penalty

repetition_penalty

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_p

Max Output Tokens

16,384

Data policy

Prompt retention: Not retained — every host this model runs on is configured not to retain prompts
Training: Not used for training

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Measured performance

Time to first response (p50)1.9s

Throughput (p50)19 tokens/s

Measured through FastMetal's own gateway over the last 30 days (656 first-response samples).

Throughput is sampled once a day: the median of 27 observations over the last 30 days.

Time to first response is measured to the first streamed chunk; throughput counts all output tokens, including reasoning tokens. These are observations, not a performance guarantee.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "llama-4-maverick",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Llama 4 Maverick actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

To count the number of 'r's in 'strawberry', I will break down the task into steps. 1. **Write down the word**: The word given is 'strawberry'. 2. **Spell out the word**: Let's spell it out letter by letter: s-t-r-a-w-b-e-r-r-y. 3. **Identify the 'r's**: Now, I'll go through the letters one by one to identify the 'r's. - 's' is not 'r'. - 't' is not 'r'. - 'r' is 'r'. (1st 'r') - 'a' is not 'r'. - 'w' is not 'r'. - 'b' is not 'r'. - 'e' is not 'r'. - 'r' is 'r'. (2nd 'r') - 'r' is 'r'. (3rd 'r') - 'y' is not 'r'. 4. **Count the 'r's**: I found 3 'r's in the word 'strawberry'. Therefore, the number of 'r's in 'strawberry' is 3.

8.5s response252 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

# Step-by-step analysis of the problem: 1. **Understanding the error message**: The error message indicates that the code is trying to read the `map` property of an undefined object. This suggests that the `users` variable is `undefined` when the `UserList` component is rendered. 2. **Identifying the source of the error**: The error occurs in the `UserList` component, specifically on line 12, where it tries to call `users.map()`. 3. **Analyzing the component code**: The `UserList` component expects a `users` prop, which is expected to be an array, as it's being used with the `map()` method. 4. **Determining why `users` is `undefined`**: The `users` prop is likely not being passed to the `Use…

15.7s response496 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

### Review and Improvements The given Python function `get_data` is designed to fetch data from a specified URL, retrying up to a certain number of times if the request fails. Here's a review of the function with suggestions for improvements in readability, performance, and adherence to best practices. #### Original Function Issues 1. **Imports Inside the Function**: The imports are inside the function. In Python, it's a best practice to place imports at the top of the file. 2. **Broad Exception Handling**: The function catches all exceptions, which can mask bugs and make debugging harder. 3. **Magic Numbers and Hardcoded Values**: The function uses magic numbers (e.g., `10` for timeout,…

24.4s response803 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Llama 4 Maverick API cost?: On FastMetal, Llama 4 Maverick is billed per token: $0.22 per 1M input tokens and $0.88 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Llama 4 Maverick with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "llama-4-maverick" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Llama 4 Maverick?: 1,048,576 tokens, shared between the prompt and the response.
What do I need to try Llama 4 Maverick?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.