Ministral 3 3B

VisionTool use

Mistral's ultra-efficient 3B parameter model with vision support. Designed for edge and low-latency applications.

Model id — paste this in your code

mistralai/ministral-3-3b

Pricing · per 1M tokens

1 Pulse = 1 DA

Input18 Pulses= 18 DA

Output18 Pulses= 18 DA

Cached input18 Pulses= 18 DA

Context window256KMax output: 32K

Capabilities

Vision — Understands images and documents you send
Tool use — Can call your functions / tools

Estimate your cost

Input tokens Output tokens Requests

Estimated cost

Use this model

Create an account, top up in dinars and call it with your key:

from openai import OpenAI

client = OpenAI(
    base_url="https://dztokens.com/v1",
    api_key="sk-dz-…",
)

reply = client.chat.completions.create(
    model="mistralai/ministral-3-3b",
    messages=[{"role": "user", "content": "Salam!"}],
)
print(reply.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://dztokens.com/v1",
  apiKey: process.env.DZTOKENS_API_KEY,
});

const reply = await client.chat.completions.create({
  model: "mistralai/ministral-3-3b",
  messages: [{ role: "user", content: "Salam!" }],
});
console.log(reply.choices[0].message.content);

curl https://dztokens.com/v1/chat/completions \
  -H "Authorization: Bearer $DZTOKENS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/ministral-3-3b",
    "messages": [{"role": "user", "content": "Salam!"}],
    "stream": true
  }'

from anthropic import Anthropic

client = Anthropic(
    base_url="https://dztokens.com",
    api_key="sk-dz-…",
)

msg = client.messages.create(
    model="mistralai/ministral-3-3b",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Salam!"}],
)
print(msg.content[0].text)

Create a free account Console

More from Mistral

mistralai/mistral-small-2603Mistral

mistralai/mistral-small-2603

Input27 Pulses

Output108 Pulses

Context350K

Mistral SmallMistral

mistralai/mistral-small-3.2-24b-instruct

Mistral's efficient 24B model optimized for simple tasks with low latency and 128K context. Great for classification, customer support, text generation, and multimodal tasks.

Input13.5 Pulses

Output36 Pulses

Context128K

mistralai/mistral-large-2512Mistral

mistralai/mistral-large-2512

Input90 Pulses

Output270 Pulses

Context256K

Magistral Small 1.2Mistral

mistralai/magistral-small-1.2

Mistral's reasoning-focused small model with vision capabilities. Optimized for step-by-step reasoning tasks.

Input90 Pulses