Mistral: Mistral Small 3

Efficient Mistral model for fast chat, extraction, and production assistants

Model lab: Mistral
Model family: mistral-small

Modalitiestext → text

Context window32,768

Maximum output16,384

InputUSD 0.04 / 1M tokens

OutputUSD 0.064 / 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/mistral-small-24b-instruct-2501.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/mistral-ai/mistral-small-24b-instruct-2501"

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.

Mistral Small 3 API Pricing

Type	Price information
Input	USD 0.04 / 1M tokens
Output	USD 0.064 / 1M tokens

Benchmarks

Intelligence Index · v4.36.7

Coding Index—

Agentic Index—

Performance

Measured on the Moduck gateway across live traffic, hour by hour over the last 24 hours. Time to first token is how long before anything appears; throughput is how fast the answer is written after that; end-to-end latency is the whole round trip. Figures are medians unless the card says otherwise.

Artificial Analysis measurement

Output speed41 tokens/s

Time to first token1.06 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput41 tok/sCurrent

Time to first token1.06 sCurrent

End-to-end latency7.7 sCurrent

Throughput

Current41 tok/s

Window average41.6 tok/s

Time to first token

Current1.06 s

Window average1.2 s

End-to-end latency

Current7.7 s

Window average7.4 s

Tail latency (P99)

Current13.2 s

Window average16.6 s

Prompt cache hit rate

Current18.0%

Window average24.7%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime is the share of time at least one provider serving this model responded. Availability is stricter: the share of requests actually served. A provider that answers but fails part of the traffic lowers availability without lowering uptime. Both cover the last three days.

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Mistral Small 3 Compare models

Model	Input price	Output price	Context window	Capabilities
Mistral Small 3This page	USD 0.04 / 1M tokens	USD 0.064 / 1M tokens	32,768	Text output
Mistral Small (latest)	USD 0.12 / 1M tokens	USD 0.48 / 1M tokens	256,000	Text output · Reasoning · Tool calling
Mistral Small 4	USD 0.12 / 1M tokens	USD 0.48 / 1M tokens	256,000	Text output · Reasoning · Tool calling
Mistral Small 3.2	USD 0.06 / 1M tokens	USD 0.16 / 1M tokens	128,000	Text output · Tool calling
Mistral Small 3.2 24B	USD 0.075 / 1M tokens	USD 0.2 / 1M tokens	256,000	Text output · Tool calling

Model specifications

Input: text
Output: text
Context window: 32,768
Maximum output: 16,384
Release date: 2025-01-30
Attachments: No
Reasoning: No
Tool calling: No
Structured output: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Mistral Small 3 for?

Efficient Mistral model for fast chat, extraction, and production assistants

What inputs and outputs does Mistral Small 3 support?

Recorded inputs: text; outputs: text.

How is Mistral Small 3 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.04 / 1M tokens; Output USD 0.064 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Mistral Small 3?

Current model records list Context window 32,768 tokens; Maximum output 16,384 tokens.

What model parameter does the Quickstart use?

The example uses moduck/mistral-ai/mistral-small-24b-instruct-2501. 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.