How much does Mistral Medium 3.5 cost?

Billing is usage-based: $1.5 per million input tokens and $7.5 per million output tokens. There is no fixed monthly fee. You pay only for what you use.

Is Mistral Medium 3.5 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 Mistral Medium 3.5 optimized for?

It is a dense 128B instruction-following model tuned for agentic workflows, coding and complex multi-step tasks, and it accepts image input alongside text.

How is Mistral Medium 3.5 different from Medium 3?

It is a newer revision of the Medium tier with a larger context window and a stronger focus on agentic and coding tasks. Choose 3.5 for the latest behavior; both accept text and image input.

Mistral: Mistral Medium 3.5: AI model

Mistral Medium 3.5 is a dense 128B instruction-following model for agentic workflows and coding, with text and image input and a 256K-token context. Reachable from inside Iran through Hormouz.

Context window:: 262,144 tokens
Input:: $1.5/1M tokens
Output:: $7.5/1M tokens
Type:: text, image

Vision
Tools
Streaming
Long context

Thinking levels: high · none

Mistral Medium 3.5 is a dense 128B-parameter instruction-following model from the Mistral family. It refines the Medium tier with a focus on agentic workflows, coding and complex, multi-step tasks, and it accepts both text and image input.

With a large 256K-token context window and tool-calling support, it is well suited to coding agents, tool-using assistants and workloads that combine long context with multimodal input. 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: $1.5 per million input tokens and $7.5 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

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-medium-3-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

Vendor	Mistral AI
Type	Text, Image
Context window	262,144 tokens
Pricing	$1.50/M in · $7.50/M out
API	Chat Completions
Capabilities	Streaming · Vision · Tools

Benchmarks

14.2

Intelligence Index

Better than 24% of models we compared

46.9

Coding Index

Better than 52% of models we compared

Agentic Index

Better than 33% of models we compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

74.8%

HLE

Humanity's Last Exam

13.8%

IFBench

Instruction-following

68.8%

AA-LCR

Long-context reasoning

69.3%

CritPt

Research-level physics reasoning

AA Omniscience

Broad factual knowledge accuracy

24.7%

Non-Hallucination

Rate of avoiding fabricated answers

18.4%

Coding

SciCode

Python for scientific computing

40.2%

Terminal-Bench Hard

Agentic coding & terminal use

33.3%

Agentic

τ²-Bench

Tool-use agents in dual-control scenarios

94.2%

GDPval

Economically valuable tasks

13.2%

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-medium-3-5",
    "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-medium-3-5",
    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-medium-3-5",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Mistral: Mistral Medium 3.5 API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Mistral: Mistral Medium 3.5 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 Medium 3.5 cost?: Billing is usage-based: $1.5 per million input tokens and $7.5 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Mistral Medium 3.5 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 Medium 3.5 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 Mistral Medium 3.5 optimized for?: It is a dense 128B instruction-following model tuned for agentic workflows, coding and complex multi-step tasks, and it accepts image input alongside text.
How is Mistral Medium 3.5 different from Medium 3?: It is a newer revision of the Medium tier with a larger context window and a stronger focus on agentic and coding tasks. Choose 3.5 for the latest behavior; both accept text and image input.

Updated 2026-10-13