How much does Devstral 2 cost?

Billing is usage-based: $0.4 per million input tokens and $2 per million output tokens. There is no fixed monthly fee. You pay only for what you use.

Is Devstral 2 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 makes Devstral 2 suited to agentic coding?

It pairs a large 256K-token context with tool calling, so it can hold much of a codebase in view, plan multi-step changes and edit across files. The loop that coding agents need.

Is Devstral 2 open weight?

Yes, it is an open-weight model from the Mistral family. On Hormouz you access it as a hosted API, so you do not need to run the 123B model yourself to use it.

Mistral: Devstral 2 2512: AI model

Devstral 2 is Mistral's open-weight agentic-coding model. A 123B dense transformer with a 256K-token context for exploring codebases and multi-step software work, reachable from inside Iran through Hormouz.

Context window:: 262,144 tokens
Input:: $0.4/1M tokens
Output:: $2/1M tokens
Type:: text

Tools
Streaming
Long context

Devstral 2 is an open-weight model from the Mistral family specialized for agentic coding. The kind of work where a model reads a codebase, plans a change, edits multiple files and iterates. It is a 123B-parameter dense transformer with a 256K-token context window, so it can keep a lot of a project in view at once.

The large context and tool-calling support make it a good backbone for coding agents, refactoring tools and automated software tasks rather than one-off snippets. 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: $0.4 per million input tokens and $2 per million output tokens. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/devstral-2512",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

Vendor	Mistral AI
Type	Text
Context window	262,144 tokens
Pricing	$0.40/M in · $2.00/M out
API	Chat Completions
Capabilities	Streaming · Tools

Benchmarks

8.6

Intelligence Index

Better than 7% of models we compared

31.3

Coding Index

Better than 34% of models we compared

2.3

Agentic Index

Better than 27% of models we compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

59.4%

HLE

Humanity's Last Exam

3.6%

IFBench

Instruction-following

38.1%

AA-LCR

Long-context reasoning

32.3%

CritPt

Research-level physics reasoning

AA Omniscience

Broad factual knowledge accuracy

20.8%

Non-Hallucination

Rate of avoiding fabricated answers

14.7%

Coding

SciCode

Python for scientific computing

32.8%

Terminal-Bench Hard

Agentic coding & terminal use

18.9%

Agentic

τ²-Bench

Tool-use agents in dual-control scenarios

24.9%

GDPval

Economically valuable tasks

2.4%

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

Buy the Mistral: Devstral 2 2512 API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Mistral: Devstral 2 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 Devstral 2 cost?: Billing is usage-based: $0.4 per million input tokens and $2 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Devstral 2 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 Devstral 2 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 makes Devstral 2 suited to agentic coding?: It pairs a large 256K-token context with tool calling, so it can hold much of a codebase in view, plan multi-step changes and edit across files. The loop that coding agents need.
Is Devstral 2 open weight?: Yes, it is an open-weight model from the Mistral family. On Hormouz you access it as a hosted API, so you do not need to run the 123B model yourself to use it.

Updated 2026-10-13