How much does the Voxtral Mini 3B API cost?

On FastMetal, Voxtral Mini 3B is billed per token in yen: ¥8.4 per 1M input tokens and ¥8.4 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Voxtral Mini 3B with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "mistral-voxtral-mini-3b-2507" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Voxtral Mini 3B?

32,768 tokens, shared between the prompt and the response.

What do I need to try Voxtral Mini 3B?

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

mistralai/voxtral-mini-3b-2507

Voxtral Mini 3B

A 3B-parameter speech-language model built on the Ministral-3B backbone with an audio encoder for state-of-the-art audio understanding. Supports speech transcription, translation, audio Q&A, and voice-to-function calling across 8 languages.

32,768 tokens

Input: ¥8.4/M

Output: ¥8.4/M

Try in Chat Get API Key

Specifications

Modalities

Input

audio

text

Output

text

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "mistral-voxtral-mini-3b-2507",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Voxtral Mini 3B 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.

Let's count the number of 'r's in 'strawberry' step by step: 1. **Identify the word**: The word to be analyzed is **strawberry**. 2. **Count occurrences**: Check each letter in the word **strawberry**: - **First 'r'** in **straw** + **Second 'r'** in **berry** = **2 occurrences**. 3. **Justify the count**: The 'r' appears twice in the sequence 'strawberry'. So, the count is justified as mentioned in the first two steps. Thus, there are **2 'r's** in **strawberry**.

0.9s response135 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…

The error `TypeError: Cannot read properties of undefined (reading 'map')` indicates that the `users` prop you passed to the `UserList` component is undefined. This happens because `users` could be falsy (e.g., `null`, `Undefined` or an empty array). Here’s how you can fix the issue: 1. **Check if `users` is undefined:** Add a check to see if `users` was defined before using it. This way, you can handle the null or undefined case gracefully: ```javascript function UserList({ users }) { if (!users) { return <p>No users available</p>; } return ( <ul> {users.map(user => <li key={user.id}>{user.name}</li>)} </ul> ); } ``` 2. **Conditionally render the component:…

1.8s response390 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):…

Certainly! Below are my suggestions for improving the readability, performance, and best practices of the given Python function. ### Improved Function ```python import requests import time import json from typing import List, Dict def get_data(url: str, retries: int = 3) -> List[Dict[str, str]]: # Use a list to accumulate results result = [] for _ in range(retries): try: response = requests.get(url, timeout=10) response.raise_for_status() # Raise an HTTPError if the HTTP request returned an error data = response.json() # Iterate over items and update result list for item in data: if item["ac…

2.8s response612 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Voxtral Mini 3B API cost?: On FastMetal, Voxtral Mini 3B is billed per token in yen: ¥8.4 per 1M input tokens and ¥8.4 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Voxtral Mini 3B with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "mistral-voxtral-mini-3b-2507" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Voxtral Mini 3B?: 32,768 tokens, shared between the prompt and the response.
What do I need to try Voxtral Mini 3B?: 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.

Try Voxtral Mini 3B right now

Voxtral Mini 3B is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.

Create a free account

More from Mistral