How much does Mistral Large 2407 cost?

Billing is usage-based: $2 per million input tokens and $6 per million output tokens. There is no fixed monthly fee. You pay only for what you use.

Is Mistral Large 2407 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.

Why use the dated 2407 build instead of the rolling Mistral Large id?

A dated build gives you stable, reproducible behavior: it will not change under you when the rolling alias is updated. Pin to 2407 when you have validated your prompts against that specific version.

What is Mistral Large 2407 good at?

As a Large 2 flagship it is strong at reasoning, code generation, structured output such as JSON, and multilingual chat, with a 128K-token context window for longer inputs.

Mistral Large 2407: AI model

Mistral Large 2407 is the pinned July-2024 build of Mistral Large 2. A weights-available flagship strong at reasoning, code and multilingual chat, with a 128K-token context, reachable from inside Iran through Hormouz.

Context window:: 131,072 tokens
Input:: $2/1M tokens
Output:: $6/1M tokens
Type:: text

Tools
Streaming
Long context

Mistral Large 2407 is the specific July-2024 build of Mistral Large 2. Pinning to a dated version is useful when you want stable, reproducible behavior that will not shift as a rolling alias is updated. It is a weights-available flagship strong at reasoning, code, JSON and multilingual chat.

It offers a 128K-token context window and tool calling, so it fits complex assistants and structured-output workflows where consistency across runs matters. 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: $2 per million input tokens and $6 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here....

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-large-2407",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

Vendor	Mistral AI
Type	Text
Context window	131,072 tokens
Pricing	$2.00/M in · $6.00/M out
API	Chat Completions
Capabilities	Streaming · Tools

Benchmarks

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

48.6%

HLE

Humanity's Last Exam

3.3%

IFBench

Instruction-following

31.2%

CritPt

Research-level physics reasoning

AA Omniscience

Broad factual knowledge accuracy

19.9%

Non-Hallucination

Rate of avoiding fabricated answers

32.3%

Coding

Terminal-Bench Hard

Agentic coding & terminal use

6.1%

Agentic

τ²-Bench

Tool-use agents in dual-control scenarios

30.7%

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-large-2407",
    "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-large-2407",
    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-large-2407",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Mistral Large 2407 API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Mistral Large 2407 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 Large 2407 cost?: Billing is usage-based: $2 per million input tokens and $6 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Mistral Large 2407 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 Large 2407 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.
Why use the dated 2407 build instead of the rolling Mistral Large id?: A dated build gives you stable, reproducible behavior: it will not change under you when the rolling alias is updated. Pin to 2407 when you have validated your prompts against that specific version.
What is Mistral Large 2407 good at?: As a Large 2 flagship it is strong at reasoning, code generation, structured output such as JSON, and multilingual chat, with a 128K-token context window for longer inputs.

Updated 2026-10-13