How much does Mistral Small 4 cost?

Billing is usage-based: $0.1875 per million input tokens and $0.75 per million output tokens. There is no fixed monthly fee. You pay only for what you use.

Is Mistral Small 4 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.

What is new in Mistral Small 4?

It unifies reasoning and multimodal strengths that earlier Mistral models split across separate systems, so one compact model handles more on its own, with image input and a large 256K-token context window.

Does Mistral Small 4 support vision and tools?

Yes. It accepts text and image input and supports tool calling, making it suitable for multimodal assistants and agentic workflows at a small-model price point.

Mistral: Mistral Small 4: AI model

Mistral Small 4 is the next Small-family release, unifying reasoning and multimodal strengths of earlier Mistral models with a 256K-token context and vision input. Reachable from inside Iran through Hormouz.

Context window:: 262,144 tokens
Input:: $0.15/1M tokens
Output:: $0.6/1M tokens
Type:: text, image

Vision
Tools
Streaming
Long context

Thinking levels: high · none

Mistral Small 4 is the next major release in the Small family. It brings together the reasoning and multimodal strengths that were spread across several earlier Mistral models into a single system, so a compact model can cover more ground on its own.

It accepts text and image input, offers a large 256K-token context window, and supports tool calling. A capable, cost-conscious default for assistants, multimodal tasks and agentic workflows. 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: $0.1875 per million input tokens and $0.75 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/mistral-small-2603",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

Vendor	Mistral AI
Type	Text, Image
Context window	262,144 tokens
Pricing	$0.15/M in · $0.60/M out
API	Chat Completions
Capabilities	Streaming · Vision · Tools

Benchmarks

11.3

Intelligence Index

Better than 17% of models we compared

26.6

Coding Index

Better than 29% of models we compared

0.8

Agentic Index

Better than 4% of models we compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

76.9%

HLE

Humanity's Last Exam

9.9%

IFBench

Instruction-following

48.2%

AA-LCR

Long-context reasoning

49.7%

CritPt

Research-level physics reasoning

0.3%

AA Omniscience

Broad factual knowledge accuracy

21.7%

Non-Hallucination

Rate of avoiding fabricated answers

33.5%

Coding

SciCode

Python for scientific computing

38.8%

Terminal-Bench Hard

Agentic coding & terminal use

17.4%

Agentic

τ²-Bench

Tool-use agents in dual-control scenarios

41.2%

GDPval

Economically valuable tasks

Source: Artificial Analysis

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/mistral-small-2603",
    "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/mistral-small-2603",
    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/mistral-small-2603",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Mistral: Mistral Small 4 API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Mistral: Mistral Small 4 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 Mistral Small 4 cost?: Billing is usage-based: $0.1875 per million input tokens and $0.75 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Mistral Small 4 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 Mistral Small 4 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.
What is new in Mistral Small 4?: It unifies reasoning and multimodal strengths that earlier Mistral models split across separate systems, so one compact model handles more on its own, with image input and a large 256K-token context window.
Does Mistral Small 4 support vision and tools?: Yes. It accepts text and image input and supports tool calling, making it suitable for multimodal assistants and agentic workflows at a small-model price point.

Updated 2026-10-13