Which is cheaper, Qwen2.5 VL 72B Instruct or Qwen2.5 Coder 32B Instruct?

Qwen2.5 Coder 32B Instruct is the cheaper of the two: one 1,000-word request costs about 626 toman.

Which one has the larger context window?

Qwen2.5 VL 72B Instruct, with 128,000 tokens.

Qwen2.5 VL 72B Instruct vs Qwen2.5 Coder 32B Instruct

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.

Feature	Qwen2.5 VL 72B Instruct	Qwen2.5 Coder 32B Instruct
Provider	Qwen (Alibaba)	Qwen (Alibaba)
Model id	qwen/qwen2.5-vl-72b-instruct	qwen/qwen-2.5-coder-32b-instruct
Context	128,000 tokens	32,768 tokens
Max output	115,200 tokens	29,491 tokens
Input / 1M tokens	232,100 toman	191,483 toman
Output / 1M tokens	290,125 toman	290,125 toman
≈ one 1,000-word request	679 toman	626 toman
Input caching	116,050 toman / 1M	No
Image input	Yes	No
File input	No	No
Tool calling	No	No
JSON output	Yes	No
Reasoning mode	No	No

Which one for what?

Qwen2.5 VL 72B Instruct

Reading screenshots, invoices, and scanned forms

679 toman per 1,000 words · Model page

Qwen2.5 Coder 32B Instruct

Chat, summarising, and everyday text generation

626 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": "qwen/qwen2.5-vl-72b-instruct",
    "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="qwen/qwen2.5-vl-72b-instruct",
    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: "qwen/qwen2.5-vl-72b-instruct",
  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' => 'qwen/qwen2.5-vl-72b-instruct',
    '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:    "qwen/qwen2.5-vl-72b-instruct",
		Messages: []openai.ChatCompletionMessageParamUnion{openai.UserMessage("Introduce yourself in one sentence.")},
	})
	if err != nil {
		panic(err)
	}
	fmt.Println(resp.Choices[0].Message.Content)
}

model = "qwen/qwen-2.5-coder-32b-instruct"

More comparisons: all pairs · model rankings · full catalogue

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