Hormouz AIHormouzSign in

Mistral: Ministral 3 8B 2512: AI model

Ministral 3 8B is the balanced Ministral 3 model. An efficient small text-and-vision model with a 256K-token context that trades size for throughput and cost, reachable from inside Iran through Hormouz.

Context window:
262,144 tokens
Input:
$0.15/1M tokens
Output:
$0.15/1M tokens
Type:
text, image
  • Vision
  • Tools
  • Streaming
  • Long context

Ministral 3 8B sits in the middle of the Ministral 3 family, balancing capability against speed and cost. It accepts text and image input and offers a 256K-token context window, making it a versatile default when 3B feels too limited and 14B is more than you need.

It supports tool calling, so it works well as the engine behind assistants, extraction pipelines and lightweight agents. 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: $0.3 per million input tokens and $0.3 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.

A balanced model in the Ministral 3 family, Ministral 3 8B 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-8b-2512",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorMistral AI
TypeText, Image
Context window262,144 tokens
Pricing$0.15/M in · $0.15/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

5.5
Intelligence Index
Better than 2% of models we compared
9.7
Coding Index
Better than 5% of models we compared
0.6
Agentic Index
Better than 2% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
47.1%
HLE
Humanity's Last Exam
4.3%
IFBench
Instruction-following
29.1%
AA-LCR
Long-context reasoning
25.7%
CritPt
Research-level physics reasoning
0%
AA Omniscience
Broad factual knowledge accuracy
13%
Non-Hallucination
Rate of avoiding fabricated answers
5.8%

Coding

SciCode
Python for scientific computing
20.7%
Terminal-Bench Hard
Agentic coding & terminal use
4.5%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
26.6%
GDPval
Economically valuable tasks
0%

Source: Artificial Analysis

3D
Top 85%
1,042Elo
Win rate: 46.2%Avg time: 33.2s
Code
Top 83%
1,059Elo
Win rate: 42.9%Avg time: 52.9s
Game Dev
Top 88%
1,003Elo
Win rate: 38.7%Avg time: 51.3s
Website
Top 80%
1,072Elo
Win rate: 42.9%Avg time: 56.1s

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-8b-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-8b-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-8b-2512",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Mistral: Ministral 3 8B 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 8B 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 8B cost?
Billing is usage-based: $0.3 per million input tokens and $0.3 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Ministral 3 8B 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 8B 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.
Where does Ministral 3 8B fit among the family?
It is the balanced middle option: more capable than the 3B, cheaper and faster than the 14B. It is a solid default for assistants, extraction and lightweight agents that also need image input.
Does Ministral 3 8B accept images and tool calls?
Yes to both. It supports image input alongside text and supports tool calling, so it can drive multimodal assistants and tool-using workflows.

Updated 2026-10-13