uttapen

DeepSeek V4 Pro 0813 API: toman pricing and code

deepseek/deepseek-v4-pro-0813

toolsreasoningjson
Input · per 1M tokens
304,457 toman
Output · per 1M tokens
913,372 toman
One 1,000-word request ≈
1,583 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 10,149 toman / 1M.Pricing and top-ups

DeepSeek V4 Pro 0813 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-v4-pro-0813",
    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)

What is DeepSeek V4 Pro 0813 good for?

DeepSeek V4 Pro 0813 comes from DeepSeek; in uttapen you reach it with the model id "deepseek/deepseek-v4-pro-0813". 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 384,000 tokens. On price it sits in the "mid-range" band — cheaper than 252 and dearer than 154 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 304,457 toman per 1M tokens and output at 913,372 — output costs 3× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 10,149 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 Nemotron 3 Ultra: DeepSeek V4 Pro 0813 works out roughly 1.1× more expensive, 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 63 thousand-word requests on DeepSeek V4 Pro 0813, and every 1,000 toman is about 632 words of round trip. A job with one million input tokens and one million output tokens comes to 1,217,829 toman in total. Filling this model's 1,048,576-token window costs 319,246 toman on the input side alone, which is the real reason to keep conversation history short.

This id gets confused with "deepseek/deepseek-v4-pro-0813:batch", because the underlying model is the same. The difference is the suffix: no suffix (the standard variant) against "batch". On a thousand-word request this variant works out 1.3× cheaper (1,583 against 1,991 toman). Maximum answer length differs as well: 384,000 against 943,718 tokens. On parameters, this one takes logprobs, seed, top_logprobs.

DeepSeek has 17 models in our catalogue; the cheapest is DeepSeek V4 Flash Latest at 79 toman per thousand words and the dearest DeepSeek V4 Pro 0813 (batch) at 1,991. Among the less common parameters it accepts logit_bias, logprobs, min_p, reasoning_effort, repetition_penalty, top_k — all through the standard request body. By context size the nearest option from another provider is Gemini 2.5 Flash 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

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

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 out822 toman
Summarising a ten-page document4,000 in + 600 out1,766 toman
Classifying a thousand short rows120,000 in + 20,000 out54,802 toman

Other variants of this model

Same core model, different execution terms and different price. This page is the standard variant.

VariantModel idOutput / 1MContext
batch (cheaper, slower)deepseek/deepseek-v4-pro-0813:batch1,148,8951,048,576

Put the variant's id verbatim in the model field; nothing else in your code changes.

Price history

DateInput (toman/1M)Output (toman/1M)
2026-09-07304,457913,372
2026-09-07323,605970,816
2026-09-07325,137975,412
2026-09-06168,122504,365

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

Frequently asked

How do I call DeepSeek V4 Pro 0813 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-v4-pro-0813". Nothing else in your code changes.
What does DeepSeek V4 Pro 0813 cost in toman?
304,457 toman per 1M input tokens and 913,372 toman per 1M output tokens; a 1,000-word request is around 1,583 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does DeepSeek V4 Pro 0813 take?
Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 384,000 tokens.
Does DeepSeek V4 Pro 0813 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.