uttapen
Create an API key

Devstral 2 2512 API: toman pricing and code

mistralai/devstral-2512

toolsjsonfiles
Create a keyTry it
Input · per 1M tokens
116,050 toman
Output · per 1M tokens
580,250 toman
One 1,000-word request ≈
905 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 11,605 toman / 1M.Pricing and top-ups

Devstral 2 2512 example: tool calling

The example is picked from this model's own capabilities. Drop in your key and it runs as is.

from openai import OpenAI
import json

client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")

tools = [{
    "type": "function",
    "function": {
        "name": "check_stock",
        "description": "Returns the stock level of a product",
        "parameters": {
            "type": "object",
            "properties": {"sku": {"type": "string"}},
            "required": ["sku"],
        },
    },
}]

messages = [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}]
first = client.chat.completions.create(model="mistralai/devstral-2512", messages=messages, tools=tools)
call = first.choices[0].message.tool_calls[0]

# you run the function yourself — the model never touches the database
args = json.loads(call.function.arguments)
result = {"sku": args["sku"], "qty": 7}

messages += [first.choices[0].message, {"role": "tool", "tool_call_id": call.id, "content": json.dumps(result)}]
final = client.chat.completions.create(model="mistralai/devstral-2512", messages=messages, tools=tools)
print(final.choices[0].message.content)

What is Devstral 2 2512 good for?

The id for Devstral 2 2512 in our API is "mistralai/devstral-2512", served from Mistral. Context is 262,144 tokens; past that you have to summarise the history yourself. A single response can run to 209,715 tokens. On price it sits in the "cheap" band — cheaper than 200 and dearer than 206 of the other paid models in the catalogue.

What it can do beyond plain text: it takes files such as PDFs as input; it supports tool calling, so it can invoke your own functions with valid arguments; it returns schema-valid JSON through response_format, ready to hand to your code. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper.

Pricing is 116,050 toman per 1M input tokens and 580,250 per 1M output tokens. A 1,000-word round trip on Devstral 2 2512 lands near 905 toman. It supports cached input: repeated context is billed at 11,605 toman per 1M, which matters a lot if your system prompt is long. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.

The closest alternative with the same capabilities from a different provider is GPT-3.5 Turbo (older v0613): Devstral 2 2512 works out roughly 1.2× cheaper, and its context window is larger. Both run on the same key and the same code, so trying the other one is a single string change.

To make the figure concrete: 100,000 toman of credit buys roughly 110 thousand-word requests on Devstral 2 2512, and every 1,000 toman is about 1,105 words of round trip. A job with one million input tokens and one million output tokens comes to 696,300 toman in total. Filling this model's 262,144-token window costs 30,422 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "mistralai/codestral-2508", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 2× dearer (905 against 453 toman). The context windows differ too: 262,144 against 256,000 tokens. Maximum answer length differs as well: 209,715 against 204,800 tokens. On parameters the other takes prediction.

Mistral has 20 models in our catalogue; the cheapest is Mistral Nemo at 18 toman per thousand words and the dearest Mistral Medium 3.5 at 3,394. It does not support include_reasoning, reasoning, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is Trinity Large Thinking at 262,144 tokens.

Good fits: high-volume work such as classification, tagging and bulk summarising, agents that reach out to APIs and databases, extracting data against a fixed schema, analysing a long document or codebase in one request.

Provider's own description

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...

Three real jobs, priced on this model

Each figure is derived from the prices above and moves when they do.

JobTokensCost
One chat turn with a medium history1,500 in + 400 out406 toman
Summarising a ten-page document4,000 in + 600 out812 toman
Classifying a thousand short rows120,000 in + 20,000 out25,531 toman

Frequently asked

How do I call Devstral 2 2512 from Iran?
Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "mistralai/devstral-2512". Nothing else in your code changes.
What does Devstral 2 2512 cost in toman?
116,050 toman per 1M input tokens and 580,250 toman per 1M output tokens; a 1,000-word request is around 905 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Devstral 2 2512 take?
Up to 262,144 tokens per request, roughly 197k words. A single answer can reach 209,715 tokens.
Does Devstral 2 2512 support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Structured output through response_format works too.