Qwen: Qwen2.5 72B Instruct

Public pricingIntelligence 81/100Medium memoryOutils

Qwen2.5 72B Instruct est un modèle texte conçu pour codage, débogage et travail technique. Il associe de bonnes performances en codage, un contexte de 33K tokens et un profil à faible coût pour un travail fiable sur coding, debugging, and technical writing.

Input

$0.12/1M

Output

$0.39/1M

Cached

$0.03/1M

Batch

$0.06/1M

Calculate your Qwen2.5 72B Instruct bill.

Set your workload — see cost at your exact volume.

What would Qwen2.5 72B Instruct cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Qwen2.5 72B Instruct at a glance.

Memory

32,768

tokens

Max reply

16,384

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

qwen

Released

Sep 2024

Training cutoff

Jun 2024

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • mmlu

    86

  • mmlu_pro

    58.1

  • humaneval

    86.6

  • math

    83.1

  • livecodebench

    55.5

  • ifeval

    86.38

  • bbh

    61.87

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick Qwen2.5 72B Instruct

  • Agentic workflows that call tools or APIs.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

Alternatives

Similar models to compare.

FAQ

Qwen2.5 72B Instruct — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, Qwen2.5 72B Instruct costs roughly $25 per month. Input is $0.12 /1M tokens and output is $0.39 /1M tokens.
Qwen2.5 72B Instruct has a 32,768-token context window (medium memory — a long report or a codebase file). That means you can fit about 6,144 words of input and history in a single call.
Beyond text generation, Qwen2.5 72B Instruct supports calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
Qwen2.5 72B Instruct was released in September 2024, with training data cut off around June 2024.
Models in a similar class include Qwen3 VL 8B Thinking, Qwen3 235B A22B Thinking 2507, Qwen3 VL 30B A3B Instruct. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Qwen2.5 72B Instruct against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard