uttapen
Create an API key

DeepSeek V3.1 API: toman pricing and code

deepseek/deepseek-chat-v3.1

toolsreasoningjson
Create a keyTry it
Input · per 1M tokens
159,569 toman
Output · per 1M tokens
478,706 toman
One 1,000-word request ≈
830 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 159,569 toman / 1M.Pricing and top-ups

DeepSeek V3.1 example: JSON output against a schema

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-…")

schema = {
    "name": "ticket",
    "schema": {
        "type": "object",
        "properties": {
            "category": {"type": "string", "enum": ["fani", "mali", "forush"]},
            "priority": {"type": "integer", "minimum": 1, "maximum": 5},
            "summary": {"type": "string"},
        },
        "required": ["category", "priority", "summary"],
        "additionalProperties": False,
    },
    "strict": True,
}

resp = client.chat.completions.create(
    model="deepseek/deepseek-chat-v3.1",
    messages=[{"role": "user", "content": "Ticket: "For two days I cannot download my invoice and I was charged twice.""}],
    response_format={"type": "json_schema", "json_schema": schema},
)
print(json.loads(resp.choices[0].message.content))

What is DeepSeek V3.1 good for?

DeepSeek V3.1 comes from DeepSeek; in uttapen you reach it with the model id "deepseek/deepseek-chat-v3.1". It accepts up to 163,840 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 144,900 tokens. On price it sits in the "cheap" band — cheaper than 186 and dearer than 220 of the other paid models in the catalogue.

What it can do beyond plain text: 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.

Pricing is 159,569 toman per 1M input tokens and 478,706 per 1M output tokens. A 1,000-word round trip on DeepSeek V3.1 lands near 830 toman. It supports cached input: repeated context is billed at 159,569 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 Aion-2.0: DeepSeek V3.1 works out roughly 1.1× 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 120 thousand-word requests on DeepSeek V3.1, and every 1,000 toman is about 1,205 words of round trip. A job with one million input tokens and one million output tokens comes to 638,275 toman in total. Filling this model's 163,840-token window costs 26,144 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-r1-0528", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 1.2× cheaper (830 against 999 toman). Maximum answer length differs as well: 144,900 against 32,768 tokens.

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, repetition_penalty, top_k, top_logprobs — all through the standard request body. By context size the nearest option from another provider is Llama Guard 4 12B at 163,840 tokens.

Good fits: high-volume work such as classification, tagging and bulk summarising, logic puzzles and code review, agents that reach out to APIs and databases, extracting data against a fixed schema.

Provider's own description

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

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 out431 toman
Summarising a ten-page document4,000 in + 600 out925 toman
Classifying a thousand short rows120,000 in + 20,000 out28,722 toman

Frequently asked

How do I call DeepSeek V3.1 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-chat-v3.1". Nothing else in your code changes.
What does DeepSeek V3.1 cost in toman?
159,569 toman per 1M input tokens and 478,706 toman per 1M output tokens; a 1,000-word request is around 830 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does DeepSeek V3.1 take?
Up to 163,840 tokens per request, roughly 123k words. A single answer can reach 144,900 tokens.
Does DeepSeek V3.1 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.