Create an API key

DeepSeek V3 0324 API: toman pricing and code

deepseek/deepseek-chat-v3-0324

Tool callingJSON output
Create a keyTry it
Input · per 1M tokens
100,404 toman
Output · per 1M tokens
394,690 toman
One 1,000-word request ≈
644 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 38,084 toman per 1M tokens.Pricing and top-ups

DeepSeek V3 0324 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-v3-0324",
    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))
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-chat-v3-0324",
  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: {
      name: "ticket",
      strict: true,
      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,
      },
    },
  },
});
console.log(JSON.parse(resp.choices[0].message.content));
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-chat-v3-0324",
    "messages": [{"role": "user", "content": "Classify the ticket and give it a priority from 1 to 5."}],
    "response_format": {"type": "json_object"}
  }'

What is DeepSeek V3 0324 good for?

DeepSeek publishes this model; we expose it under the id "deepseek/deepseek-chat-v3-0324". Its context window is 163,840 tokens, roughly 123k English words in one request. A single response can run to 115,200 tokens. On price it sits in the "cheap" band — cheaper than 243 and dearer than 155 of the other paid models in the catalogue.

Capabilities available on this id: 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.

For a back-of-envelope figure: about 644 toman per 1,000-word exchange (100,404 in, 394,690 out, per 1M tokens). It supports cached input: repeated context is billed at 38,084 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 Qwen3 Next 80B A3B Instruct: DeepSeek V3 0324 works out about 20% 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 155 thousand-word requests on DeepSeek V3 0324, and every 1,000 toman is about 1,553 words of round trip. A job with one million input tokens and one million output tokens comes to 495,094 toman in total. Filling this model's 163,840-token window costs 16,450 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", and choosing between those two is where most people hesitate. Both land at nearly the same price on a thousand-word request (644 and 579 toman). Maximum answer length differs as well: 115,200 against 16,000 tokens. On parameters, this one takes logprobs, top_logprobs while the other takes logit_bias, min_p, presence_penalty, repetition_penalty.

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 logprobs, top_k, top_logprobs — 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.

What to use it for: 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, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

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 out308 toman
Summarising a ten-page document4,000 in + 600 out638 toman
Classifying a thousand short rows120,000 in + 20,000 out19,942 toman

Price history

DateInput (toman/1M)Output (toman/1M)
5 Oct 2026100,404394,690
4 Oct 202686,555346,219
28 Sep 2026100,404394,690
11 Sep 202686,555346,219
8 Sep 2026100,404394,690
8 Sep 202686,555346,219
7 Sep 2026100,404394,690
7 Sep 202686,555346,219

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

Frequently asked

How do I call DeepSeek V3 0324 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-v3-0324". Nothing else in your code changes.
What does DeepSeek V3 0324 cost in toman?
100,404 toman per 1M input tokens and 394,690 toman per 1M output tokens; a 1,000-word request is around 644 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does DeepSeek V3 0324 take?
Up to 163,840 tokens per request, roughly 123k words. A single answer can reach 115,200 tokens.
Does DeepSeek V3 0324 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.