Hormouz AIHormouzSign in

Mistral: Ministral 3 3B 2512: AI model

Ministral 3 3B is the smallest Ministral 3 model. A tiny, efficient text-and-vision model with a 128K-token context, built for edge and high-volume use, reachable from inside Iran through Hormouz.

Context window:
131,072 tokens
Input:
$0.1/1M tokens
Output:
$0.1/1M tokens
Type:
text, image
  • Vision
  • Tools
  • Streaming
  • Long context

Ministral 3 3B is the smallest member of the Ministral 3 family. A very compact model that still accepts text and image input. Its small size makes it fast and inexpensive per request, which suits high-volume workloads and latency-sensitive tasks.

With a 128K-token context window and tool-calling support, it is a good fit for simple classification, extraction, routing and assistant features where you value throughput and cost over maximum reasoning depth. It is served through Hormouz behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs unchanged.

Pricing is usage-based: $0.15 per million input tokens and $0.15 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/ministral-3b-2512",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorMistral AI
TypeText, Image
Context window131,072 tokens
Pricing$0.10/M in · $0.10/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Sizes in this family

SizeContext windowPricing
3B131,072$0.10/M in · $0.10/M out
8B262,144$0.15/M in · $0.15/M out
14B262,144$0.20/M in · $0.20/M out

Benchmarks

4.8
Intelligence Index
Better than 1% of models we compared
4.8
Coding Index
Better than 2% of models we compared
0.8
Agentic Index
Better than 4% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
35.8%
HLE
Humanity's Last Exam
5.4%
IFBench
Instruction-following
26.8%
AA-LCR
Long-context reasoning
17%
CritPt
Research-level physics reasoning
0%
AA Omniscience
Broad factual knowledge accuracy
9%
Non-Hallucination
Rate of avoiding fabricated answers
19.8%

Coding

SciCode
Python for scientific computing
15.3%
Terminal-Bench Hard
Agentic coding & terminal use
0%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
24.9%
GDPval
Economically valuable tasks
0%

Source: Artificial Analysis

3D
Top 94%
973Elo
Win rate: 35.9%Avg time: 29.2s
Code
Top 89%
1,016Elo
Win rate: 37.3%Avg time: 36.3s
Game Dev
Top 93%
961Elo
Win rate: 33%Avg time: 34.8s
Website
Top 87%
1,034Elo
Win rate: 38.2%Avg time: 37.6s

Metrics sourced from Design Arena

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/ministral-3b-2512",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="mistralai/ministral-3b-2512",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "mistralai/ministral-3b-2512",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Mistral: Ministral 3 3B 2512 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Mistral: Ministral 3 3B 2512 and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Ministral 3 3B cost?
Billing is usage-based: $0.15 per million input tokens and $0.15 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Ministral 3 3B from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.
Is Ministral 3 3B compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
When should I choose Ministral 3 3B?
Choose it for high-volume, latency-sensitive and cost-sensitive tasks. Simple classification, extraction, routing and lightweight assistant features. Where speed and price matter more than deep reasoning.
Does Ministral 3 3B support images?
Yes, it accepts image input as well as text, so even at this small size you can build lightweight multimodal features.

Updated 2026-10-13