uttapen
Create an API key

DeepSeek V3 API: toman pricing and code

deepseek/deepseek-chat

toolsjson
Create a keyTry it
Input · per 1M tokens
92,840 toman
Output · per 1M tokens
258,211 toman
One 1,000-word request ≈
456 toman

You are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups

DeepSeek V3 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",
    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 good for?

DeepSeek publishes this model; we expose it under the id "deepseek/deepseek-chat". Its context window is 163,840 tokens, roughly 123k English words in one request. A single response can run to 16,384 tokens. On price it sits in the "cheap" band — cheaper than 128 and dearer than 278 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. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper.

Pricing is 92,840 toman per 1M input tokens and 258,211 per 1M output tokens. A 1,000-word round trip on DeepSeek V3 lands near 456 toman. 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 Codestral 2508: DeepSeek V3 works out roughly 1× more expensive, and its context window is smaller. 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 219 thousand-word requests on DeepSeek V3, and every 1,000 toman is about 2,193 words of round trip. A job with one million input tokens and one million output tokens comes to 351,051 toman in total. Filling this model's 163,840-token window costs 15,211 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-chat-v3-0324", and choosing between those two is where most people hesitate. Both land at nearly the same price on a thousand-word request (456 and 471 toman). Maximum answer length differs as well: 16,384 against 147,456 tokens. On parameters the other takes logprobs, 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, min_p, repetition_penalty, top_k — all through the standard request body. 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 Llama Guard 4 12B at 163,840 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.

Provider's own description

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

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 out243 toman
Summarising a ten-page document4,000 in + 600 out526 toman
Classifying a thousand short rows120,000 in + 20,000 out16,305 toman

Frequently asked

How do I call DeepSeek V3 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". Nothing else in your code changes.
What does DeepSeek V3 cost in toman?
92,840 toman per 1M input tokens and 258,211 toman per 1M output tokens; a 1,000-word request is around 456 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does DeepSeek V3 take?
Up to 163,840 tokens per request, roughly 123k words. A single answer can reach 16,384 tokens.
Does DeepSeek V3 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.