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

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

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.