Create an API key

DeepSeek V4 Flash 0423 API: toman pricing and code

deepseek/deepseek-v4-flash

Tool callingReasoningJSON output
Create a keyTry it
Input · per 1M tokens
31,506 toman
Output · per 1M tokens
63,012 toman
One 1,000-word request ≈
123 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 6,301 toman per 1M tokens.Pricing and top-ups

DeepSeek V4 Flash 0423 example: tool calling

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-…")

tools = [{
    "type": "function",
    "function": {
        "name": "check_stock",
        "description": "Returns the stock level of a product",
        "parameters": {
            "type": "object",
            "properties": {"sku": {"type": "string"}},
            "required": ["sku"],
        },
    },
}]

messages = [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}]
first = client.chat.completions.create(model="deepseek/deepseek-v4-flash", messages=messages, tools=tools)
call = first.choices[0].message.tool_calls[0]

# you run the function yourself — the model never touches the database
args = json.loads(call.function.arguments)
result = {"sku": args["sku"], "qty": 7}

messages += [first.choices[0].message, {"role": "tool", "tool_call_id": call.id, "content": json.dumps(result)}]
final = client.chat.completions.create(model="deepseek/deepseek-v4-flash", messages=messages, tools=tools)
print(final.choices[0].message.content)
import OpenAI from "openai";

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

const tools = [{
  type: "function",
  function: {
    name: "check_stock",
    description: "Returns the stock level of a product",
    parameters: { type: "object", properties: { sku: { type: "string" } }, required: ["sku"] },
  },
}];

const messages = [{ role: "user", content: "How many of the Nike NK-42 shoe are in stock?" }];
const first = await client.chat.completions.create({ model: "deepseek/deepseek-v4-flash", messages, tools });
const call = first.choices[0].message.tool_calls[0];

const args = JSON.parse(call.function.arguments);
const result = { sku: args.sku, qty: 7 };

messages.push(first.choices[0].message, { role: "tool", tool_call_id: call.id, content: JSON.stringify(result) });
const final = await client.chat.completions.create({ model: "deepseek/deepseek-v4-flash", messages, tools });
console.log(final.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-v4-flash",
    "messages": [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "check_stock",
        "parameters": {"type": "object", "properties": {"sku": {"type": "string"}}, "required": ["sku"]}
      }
    }]
  }'

What is DeepSeek V4 Flash 0423 good for?

DeepSeek V4 Flash 0423 comes from DeepSeek; in uttapen you reach it with the model id "deepseek/deepseek-v4-flash". 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 943,717 tokens. On price it sits in the "very cheap" band — cheaper than 363 and dearer than 34 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; 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.

For a back-of-envelope figure: about 123 toman per 1,000-word exchange (31,506 in, 63,012 out, per 1M tokens). It supports cached input: repeated context is billed at 6,301 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 3.5 Lightning, and DeepSeek V4 Flash 0423 costs about the same, 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 813 thousand-word requests on DeepSeek V4 Flash 0423, and every 1,000 toman is about 8,130 words of round trip. A job with one million input tokens and one million output tokens comes to 94,518 toman in total. Filling this model's 1,048,576-token window costs 33,036 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-flash-0731", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out about 23% cheaper (123 against 162 toman). Maximum answer length differs as well: 943,717 against 943,718 tokens. On parameters, this one takes max_completion_tokens while the other takes parallel_tool_calls.

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 3,644. Among the less common parameters it accepts logit_bias, logprobs, max_completion_tokens, min_p, presence_penalty, reasoning_effort — all through the standard request body. By context size the nearest option from another provider is Ember-1 at 1,048,576 tokens.

What to use it for: 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, analysing a long document or codebase in one request.

Provider's own description

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

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 out72 toman
Summarising a ten-page document4,000 in + 600 out164 toman
Classifying a thousand short rows120,000 in + 20,000 out5,041 toman

Price history

DateInput (toman/1M)Output (toman/1M)
28 Oct 202631,50663,012
28 Oct 202648,47196,941
27 Oct 202616,38332,766
27 Oct 202615,545155,799
27 Oct 202617,311155,799
27 Oct 202648,47196,941
26 Oct 202631,50663,012
26 Oct 202617,311155,799
13 Oct 202631,50663,012
13 Oct 202617,311443,161
13 Oct 202616,999443,161
13 Oct 202615,753443,161

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

Frequently asked

How do I call DeepSeek V4 Flash 0423 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-flash". Nothing else in your code changes.
What does DeepSeek V4 Flash 0423 cost in toman?
31,506 toman per 1M input tokens and 63,012 toman per 1M output tokens; a 1,000-word request is around 123 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does DeepSeek V4 Flash 0423 take?
Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 943,717 tokens.
Does DeepSeek V4 Flash 0423 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.