Hormouz AIHormouzSign in

Mistral: Ministral 3 14B 2512: AI model

Ministral 3 14B is the largest Ministral 3 model. A compact text-and-vision model reaching near-24B capability, with a 256K-token context, reachable from inside Iran through Hormouz.

Context window:
262,144 tokens
Input:
$0.2/1M tokens
Output:
$0.2/1M tokens
Type:
text, image
  • Vision
  • Tools
  • Streaming
  • Long context

Ministral 3 14B is the top of the Ministral 3 family. A compact, efficient model that accepts both text and images while pushing performance close to larger 24B-class models. It offers a 256K-token context window, which is generous for a model of its size.

It supports tool calling and vision input, making it a practical choice when you want capable multimodal reasoning without the cost of a flagship model. 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: $0.35 per million input tokens and $0.35 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

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-14b-2512",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorMistral AI
TypeText, Image
Context window262,144 tokens
Pricing$0.20/M in · $0.20/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

6
Intelligence Index
Better than 3% of models we compared
14.4
Coding Index
Better than 12% of models we compared
1.1
Agentic Index
Better than 15% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
57.2%
HLE
Humanity's Last Exam
4.6%
IFBench
Instruction-following
32%
AA-LCR
Long-context reasoning
26.3%
CritPt
Research-level physics reasoning
0%
AA Omniscience
Broad factual knowledge accuracy
13.6%
Non-Hallucination
Rate of avoiding fabricated answers
7.5%

Coding

SciCode
Python for scientific computing
23.8%
Terminal-Bench Hard
Agentic coding & terminal use
4.5%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
27.2%
GDPval
Economically valuable tasks
0%

Source: Artificial Analysis

3D
Top 91%
1,000Elo
Win rate: 39.6%Avg time: 53.6s
Code
Top 80%
1,071Elo
Win rate: 44%Avg time: 81.9s
Game Dev
Top 82%
1,051Elo
Win rate: 43.6%Avg time: 90.6s
Website
Top 78%
1,088Elo
Win rate: 44.8%Avg time: 84.8s

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-14b-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-14b-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-14b-2512",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Mistral: Ministral 3 14B 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 14B 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 14B cost?
Billing is usage-based: $0.35 per million input tokens and $0.35 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Ministral 3 14B 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 14B 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.
Can Ministral 3 14B understand images?
Yes. It accepts both text and image input, so you can use it for multimodal tasks such as describing images or answering questions about a picture alongside text prompts.
How does Ministral 3 14B compare to the smaller Ministral 3 models?
It is the largest of the family and the most capable, reaching near-24B-class performance, while Ministral 3 8B and 3B trade capability for lower cost and higher throughput. Pick 14B when you want the best quality within the compact family.

Updated 2026-10-13