Create an API key

DeepSeek Pro Latest API: toman pricing and code

~deepseek/deepseek-pro-latest

This id is an alias that always points at the newest version of this model. Send a fixed version's id if answers must not change when a new version ships.

Tool callingReasoningJSON output
Create a keyTry it
Input · per 1M tokens
32,095 toman
Output · per 1M tokens
2,769,755 toman
One 1,000-word request ≈
3,642 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 32,095 toman per 1M tokens.Pricing and top-ups

DeepSeek Pro Latest example: a multi-step problem with reasoning

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

from openai import OpenAI

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

resp = client.chat.completions.create(
    model="~deepseek/deepseek-pro-latest",
    messages=[{"role": "user", "content": (
        "A shop has 3 warehouses. A ships 120 orders a day, B ships 85 and C ships 40. "
        "If C closes and its load is split between A and B in proportion to their capacity, how many does each ship a day? "
        "Work through it step by step and give just the two numbers at the end."
    )}],
    reasoning_effort="medium",   # low | medium | high
)
print(resp.choices[0].message.content)
# reasoning tokens count as output tokens too:
print(resp.usage.completion_tokens_details)
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "~deepseek/deepseek-pro-latest",
    "messages": [{"role": "user", "content": "120 and 85 daily orders split across two warehouses; work through it step by step."}],
    "reasoning": {"effort": "medium"}
  }'
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });

const resp = await client.chat.completions.create({
  model: "~deepseek/deepseek-pro-latest",
  messages: [{ role: "user", content: "120 and 85 daily orders are split between two warehouses; work through it step by step and give just the two numbers at the end." }],
  reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);
console.log(resp.usage.completion_tokens_details);

What is DeepSeek Pro Latest good for?

DeepSeek Pro Latest comes from DeepSeek; in uttapen you reach it with the model id "~deepseek/deepseek-pro-latest". It accepts up to 1,048,576 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 393,216 tokens. On price it sits in the "mid-range" band — cheaper than 83 and dearer than 311 of the other paid models in the catalogue.

What you get on top of text in, text out: 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; it has a reasoning mode that pays off on multi-step problems, maths and debugging. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.

Input runs at 32,095 toman per 1M tokens and output at 2,769,755 — output costs 86.3× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 32,095 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 GLM 5.3 Prime: DeepSeek Pro Latest works out about 29% 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 27 thousand-word requests on DeepSeek Pro Latest, and every 1,000 toman is about 275 words of round trip. A job with one million input tokens and one million output tokens comes to 2,801,849 toman in total. Filling this model's 1,048,576-token window costs 33,654 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "deepseek/deepseek-v4-pro", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out about 70% more expensive (3,642 against 2,160 toman). On parameters the other takes max_completion_tokens.

DeepSeek has 18 models in our catalogue; the cheapest is DeepSeek V4 Flash 0423 at 123 toman per thousand words and the dearest DeepSeek Pro Latest at 3,642. Among the less common parameters it accepts logit_bias, logprobs, min_p, presence_penalty, reasoning_effort, repetition_penalty — all through the standard request body. By context size the nearest option from another provider is Ember-1 at 1,048,576 tokens.

Where it makes sense: product chatbots and internal assistants, where cost and quality have to balance, logic puzzles and code review, 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

This model always redirects to the latest model in the DeepSeek Pro family.

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 out1,156 toman
Summarising a ten-page document4,000 in + 600 out1,790 toman
Classifying a thousand short rows120,000 in + 20,000 out59,246 toman

Price history

DateInput (toman/1M)Output (toman/1M)
5 Nov 202632,0952,769,755
5 Nov 202633,3412,769,755
31 Oct 202635,8342,769,755
31 Oct 202635,8341,384,877
29 Oct 202635,8342,769,755
28 Oct 202645,6322,769,755
28 Oct 202650,728152,184
28 Oct 202656,7452,769,755
28 Oct 202670,379211,138
28 Oct 202670,7332,769,755
28 Oct 202678,606235,817
28 Oct 202688,0092,769,755

Every price change for this model is recorded. Toman figures use today's rate.

Frequently asked

How do I call DeepSeek Pro Latest 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 "~deepseek/deepseek-pro-latest". Nothing else in your code changes.
What does DeepSeek Pro Latest cost in toman?
32,095 toman per 1M input tokens and 2,769,755 toman per 1M output tokens; a 1,000-word request is around 3,642 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does DeepSeek Pro Latest take?
Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 393,216 tokens.
Does DeepSeek Pro Latest 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.