Skip to content

Qwen2.5 72B Instruct vs Qwen3.6 Plus

Qwen2.5 72B Instruct (Qwen) and Qwen3.6 Plus (Qwen) are listed at different prices. Qwen3.6 Plus costs less for input, $0.325 per 1M tokens against $0.36; Qwen2.5 72B Instruct costs less for output, $0.40 per 1M tokens against $1.95. Qwen3.6 Plus has the larger context window, 1,000,000 tokens against 32,768 for Qwen2.5 72B Instruct. Qwen3.6 Plus charges $1.30 and $3.90 per 1M once a prompt passes 256,000 tokens; Qwen2.5 72B Instruct keeps one price across its window. Qwen2.5 72B Instruct accepts text and produces text; Qwen3.6 Plus accepts text, images and video and produces text.

Qwen2.5 72B Instruct accepts and produces text, with tools, structured outputs, and response formats; Qwen: Qwen3.6 Plus accepts text, images, and video and produces text, with those same features plus reasoning support. Their context limits are 32,768 and 1,000,000 tokens, and their output limits are 16,384 and 65,536 tokens, respectively.

Compared from catalog data checked

Qwen3.6 Plus

$0.325 in
$1.95 out
1M context

Side by side

0.00 the better figure in a row
Qwen2.5 72B Instruct and Qwen3.6 Plus specifications side by side
SpecificationQwen2.5 72B InstructQwen3.6 Plus
Maker Qwen Qwen
Added to catalog 19 Sep 2024 2 Apr 2026
Input, per 1M tokens $0.36 $0.325
Output, per 1M tokens $0.40 $1.95
Input above 256K tokensPer 1M; long prompts n/a $1.30
Output above 256K tokens n/a $3.90
Context windowTokens 32,768 1,000,000
Max outputTokens 16,384 65,536
Accepts text image, text, video
Produces text text
Tool calling Yes Yes
Structured outputs Yes Yes
Reasoning effort control No No

List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.

What the same task costs

List price for one request, from the token counts shown. The same four tasks are priced on every model page.

Check the provider's pageToken counts are estimates, and the two models count tokens differently.
Cost of the same task on Qwen2.5 72B Instruct and Qwen3.6 Plus
TaskQwen2.5 72B InstructQwen3.6 Plus
Answer a short question500 in / 300 out $0.0003 $0.0007
Summarise a 50-page PDF25,000 in / 800 out $0.0093 $0.0097
Review a 2,000-line source file30,000 in / 2,000 out $0.012 $0.014
Read a 300-page contract set150,000 in / 1,500 out $0.055 $0.052

Which to choose

Choose Qwen2.5 72B Instruct if

  • Output tokens cost less: $0.40 against $1.95 per 1M
Qwen2.5 72B Instruct details

Choose Qwen3.6 Plus if

  • Input tokens cost less: $0.325 against $0.36 per 1M
  • You need the larger context window: 1,000,000 tokens against 32,768
  • You need longer answers in one response: 65,536 tokens against 16,384
  • It has to read images and video, which the other model does not
Qwen3.6 Plus details

Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.

Comparison questions

Is Qwen2.5 72B Instruct cheaper than Qwen3.6 Plus?

It depends on the job: one costs less for input and the other for output. Qwen2.5 72B Instruct costs $0.36 per 1M input tokens and $0.40 per 1M output tokens; Qwen3.6 Plus costs $0.325 and $1.95 as checked on 22 Nov 2026.

Which has the larger context window, Qwen2.5 72B Instruct or Qwen3.6 Plus?

Qwen3.6 Plus, at 1,000,000 tokens against 32,768 for Qwen2.5 72B Instruct.

Which is better for coding, Qwen2.5 72B Instruct or Qwen3.6 Plus?

This page does not rank models on quality, and it does not repeat either maker's claims. The table shows what each accepts, supports and costs; the reliable test is your own task: give both the same piece of code and compare the answers.

Can I use both Qwen2.5 72B Instruct and Qwen3.6 Plus?

Neither is offered in the Upend chat today. Both are listed in the catalog through OpenRouter, with the figures shown here.

Find the model for your task.

Every comparison is computed from the live catalog.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.