Mistral: Ministral 3 14B 2512

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Model lab: Mistral
Model family: ministral

Modalitiestext, image → text

Context window262,144

Maximum output209,715

InputUSD 0.16 / 1M tokens

OutputUSD 0.16 / 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/ministral-14b-2512.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/mistral-ai/ministral-14b-2512"

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.

Ministral 3 14B 2512 API Pricing

Type	Price information
Input	USD 0.16 / 1M tokens
Output	USD 0.16 / 1M tokens
Cached input	USD 0.016 / 1M tokens

Performance

Performance trends

Throughput91.8 tok/sCurrent

Time to first token1.3 sCurrent

End-to-end latency7.9 sCurrent

Throughput

Current91.8 tok/s

Window average89.8 tok/s

Time to first token

Current1.3 s

Window average1.5 s

End-to-end latency

Current7.9 s

Window average7.5 s

Tail latency (P99)

Current16.6 s

Window average16.2 s

Prompt cache hit rate

Current31.1%

Window average22.5%

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

Ministral 3 14B 2512 Compare models

Model	Input price	Output price	Context window	Capabilities
Ministral 3 14B 2512This page	USD 0.16 / 1M tokens	USD 0.16 / 1M tokens	262,144	Text output · Tool calling
Ministral 3 3B	USD 0.08368 / 1M tokens	USD 0.08368 / 1M tokens	262,144	Text output · Tool calling
Ministral 3 3B 2512	USD 0.08 / 1M tokens	USD 0.08 / 1M tokens	131,072	Text output · Tool calling
Ministral 3 8B	USD 0.12 / 1M tokens	USD 0.12 / 1M tokens	262,144	Text output · Tool calling
Ministral 3 8B 2512	USD 0.12 / 1M tokens	USD 0.12 / 1M tokens	262,144	Text output · Tool calling

Model specifications

Input: text, image
Output: text
Context window: 262,144
Maximum output: 209,715
Release date: 2025-12-02
Attachments: Yes
Reasoning: No
Tool calling: Yes
Structured output: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Ministral 3 14B 2512 for?

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

What inputs and outputs does Ministral 3 14B 2512 support?

Recorded inputs: text, images; outputs: text.

How is Ministral 3 14B 2512 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.16 / 1M tokens; Output USD 0.16 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Ministral 3 14B 2512?

Current model records list Context window 262,144 tokens; Maximum output 209,715 tokens.

What model parameter does the Quickstart use?

The example uses moduck/mistral-ai/ministral-14b-2512. 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.