Which is cheaper, DeepSeek V3.1 or DeepSeek V4 Pro 0423?

DeepSeek V3.1 is the cheaper of the two: one 1,000-word request costs about 830 toman, about 1.3× cheaper than DeepSeek V4 Pro 0423.

Which one has the larger context window?

DeepSeek V4 Pro 0423, with 1,048,576 tokens.

DeepSeek V3.1 vs DeepSeek V4 Pro 0423

Both sit behind the same key and the same code on uttapen — the only thing that changes is the model string, so you can run each of them against your own workload without touching anything else. On cost, DeepSeek V3.1 comes out about 1.3× cheaper.

Feature	DeepSeek V3.1	DeepSeek V4 Pro 0423
Provider	DeepSeek	DeepSeek
Model id	deepseek/deepseek-chat-v3.1	deepseek/deepseek-v4-pro
Context	163,840 tokens	1,048,576 tokens
Max output	144,900 tokens	384,000 tokens
Input / 1M tokens	159,569 toman	277,145 toman
Output / 1M tokens	478,706 toman	554,290 toman
≈ one 1,000-word request	830 toman	1,081 toman
Input caching	159,569 toman / 1M	23,095 toman / 1M
Image input	No	No
File input	No	No
Tool calling	Yes	Yes
JSON output	Yes	Yes
Reasoning mode	Yes	Yes

Which one for what?

DeepSeek V3.1

Multi-step problems, maths, and tracking down a bug
Agents that call your own APIs and database

830 toman per 1,000 words · Model page

DeepSeek V4 Pro 0423

Multi-step problems, maths, and tracking down a bug
Whole documents or a codebase in a single request
Agents that call your own APIs and database

1,081 toman per 1,000 words · Model page

Run both with the same code

Swap the model value between the two ids and send the same request twice; what each answer cost comes back in the X-Uttapen-Cost-Toman header.

curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-chat-v3.1",
    "messages": [{"role": "user", "content": "Introduce yourself in one sentence."}],
    "stream": true
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uttapen.ir/v1",
    api_key="sk-up-…",
)

stream = client.chat.completions.create(
    model="deepseek/deepseek-chat-v3.1",
    messages=[{"role": "user", "content": "Introduce yourself in one sentence."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

import OpenAI from "openai";

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

const stream = await client.chat.completions.create({
  model: "deepseek/deepseek-chat-v3.1",
  messages: [{ role: "user", content: "Introduce yourself in one sentence." }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

<?php
// composer require openai-php/client guzzlehttp/guzzle
$client = OpenAI::factory()
    ->withBaseUri('https://api.uttapen.ir/v1')
    ->withApiKey('sk-up-…')
    ->make();

$result = $client->chat()->create([
    'model' => 'deepseek/deepseek-chat-v3.1',
    'messages' => [['role' => 'user', 'content' => 'Introduce yourself in one sentence.']],
]);
echo $result->choices[0]->message->content;

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go"
	"github.com/openai/openai-go/option"
)

func main() {
	client := openai.NewClient(
		option.WithBaseURL("https://api.uttapen.ir/v1"),
		option.WithAPIKey("sk-up-…"),
	)
	resp, err := client.Chat.Completions.New(context.Background(), openai.ChatCompletionNewParams{
		Model:    "deepseek/deepseek-chat-v3.1",
		Messages: []openai.ChatCompletionMessageParamUnion{openai.UserMessage("Introduce yourself in one sentence.")},
	})
	if err != nil {
		panic(err)
	}
	fmt.Println(resp.Choices[0].Message.Content)
}

model = "deepseek/deepseek-v4-pro"

More comparisons: all pairs · model rankings · full catalogue

base_url = https://api.uttapen.ir/v1