Mistral: Ministral 3B

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

Model lab: Mistral
Model family: ministral

Modalitiestext → text

Context window128,000

Maximum output8,192

Input · Context ≤ 128000 tokens · Maximum output 4000 tokensUSD 0.08 / 1M tokens

Output · Context ≤ 128000 tokens · Maximum output 4000 tokensUSD 0.08 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to mistral/ministral-3b.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "mistral/ministral-3b"

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 3B API Pricing

Type	Price information
Input · Context ≤ 128000 tokens · Maximum output 4000 tokens	USD 0.08 / 1M tokens
Output · Context ≤ 128000 tokens · Maximum output 4000 tokens	USD 0.08 / 1M tokens
Cached input · Context ≤ 128000 tokens · Maximum output 4000 tokens	USD 0.08 / 1M tokens
Cache write · Context ≤ 128000 tokens · Maximum output 4000 tokens	USD 0.08 / 1M tokens

Performance

Performance trends

Throughput93.3 tok/sCurrent

Time to first token1.3 sCurrent

End-to-end latency7.5 sCurrent

Throughput

Current93.3 tok/s

Window average89.2 tok/s

Time to first token

Current1.3 s

Window average1.4 s

End-to-end latency

Current7.5 s

Window average7.5 s

Tail latency (P99)

Current14.8 s

Window average16.7 s

Prompt cache hit rate

Current31.1%

Window average22.7%

Error rate

Current2.1%

Window average0.2%

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 3B Compare models

Model	Input price	Output price	Context window	Capabilities
Ministral 3BThis page	USD 0.08 / 1M tokens · Context ≤ 128000 tokens · Maximum output 4000 tokens	USD 0.08 / 1M tokens · Context ≤ 128000 tokens · Maximum output 4000 tokens	128,000	Text output · Tool calling
Ministral 8B Instruct	USD 0.12 / 1M tokens · Context ≤ 128000 tokens · Maximum output 4000 tokens	USD 0.12 / 1M tokens · Context ≤ 128000 tokens · Maximum output 4000 tokens	131,072	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

Model specifications

Input: text
Output: text
Context window: 128,000
Maximum output: 8,192
Release date: 2024-10-16
Attachments: No
Reasoning: No
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Ministral 3B for?

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

What inputs and outputs does Ministral 3B support?

Recorded inputs: text; outputs: text.

How is Ministral 3B priced?

The pricing table shows the current recorded Moduck price. For example: Input · Context ≤ 128000 tokens · Maximum output 4000 tokens USD 0.08 / 1M tokens; Output · Context ≤ 128000 tokens · Maximum output 4000 tokens USD 0.08 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Ministral 3B?

Current model records list Context window 128,000 tokens; Maximum output 8,192 tokens.

What model parameter does the Quickstart use?

The example uses mistral/ministral-3b. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

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.