Mistral: Voxtral Small 24B 2507

Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

Model lab: Mistral
Model family: voxtral

Model resources

Hugging Face

Modalitiestext, audio → text

Context window32,768

Maximum output32,768

InputUSD 0.08 / 1M tokens

OutputUSD 0.24 / 1M tokens

Try now View docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/mistral-ai/voxtral-small-24b-2507.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/mistral-ai/voxtral-small-24b-2507"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Voxtral Small 24B 2507 API Pricing

Type	Price information
Input	USD 0.08 / 1M tokens
Output	USD 0.24 / 1M tokens

Performance

Performance trends

Throughput87.5 tok/sCurrent

Time to first token1.4 sCurrent

End-to-end latency7.9 sCurrent

Throughput

Current87.5 tok/s

Window average89.6 tok/s

Time to first token

Current1.4 s

Window average1.4 s

End-to-end latency

Current7.9 s

Window average7.5 s

Tail latency (P99)

Current13.6 s

Window average17.0 s

Prompt cache hit rate

Current18.3%

Window average24.6%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Voxtral Small 24B 2507 Compare models

Model	Input price	Output price	Context window	Capabilities
Voxtral Small 24B 2507This page	USD 0.08 / 1M tokens	USD 0.24 / 1M tokens	32,768	Text output · Tool calling
Voxtral Mini 3B 2507	USD 0.032 / 1M tokens	USD 0.032 / 1M tokens	32,768	Text output · Tool calling
Voxtral Small (latest)	USD 0.08 / 1M tokens	USD 0.24 / 1M tokens	32,000	Text output · Tool calling
Mistral Large 4	USD 0.544 / 1M tokens	USD 1.672 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Mistral Medium 3.5	USD 1.2 / 1M tokens	USD 6 / 1M tokens	262,144	Text output · Reasoning · Tool calling

Model specifications

Input: text, audio
Output: text
Context window: 32,768
Maximum output: 32,768
Release date: 2025-07-15
Attachments: Yes
Reasoning: No
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Voxtral Small 24B 2507 for?

Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

What inputs and outputs does Voxtral Small 24B 2507 support?

Recorded inputs: text, audio; outputs: text.

How is Voxtral Small 24B 2507 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.08 / 1M tokens; Output USD 0.24 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Voxtral Small 24B 2507?

Current model records list Context window 32,768 tokens; Maximum output 32,768 tokens.

What model parameter does the Quickstart use?

The example uses moduck/mistral-ai/voxtral-small-24b-2507. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.