Qwen
MultimodalAUTO PROFILEPriced via OpenRouter

Qwen2.5 VL 72B Instruct

text+image->text

Qwen2.5 VL 72B Instruct is a vision-language model that takes images alongside text, built for OCR, diagram understanding, and multi-modal reasoning. Available via Qwen. 128,000-token context. Efficient pricing.

Qwen2.5 VL 72B Instruct is a multimodal AI model from Qwen. It costs $0.8000 per million input tokens and $1.00 per million output tokens (blended $0.8600/M), with a 128,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.8000/M
per million input tokens
OUTPUT
$1.00/M
per million output tokens
BLENDED 70/30
$0.8600/M

0.0%over 10 days · hover to read

Qwen2.5 VL 72B Instruct — blended price

Reconstructed from 10 days of recorded rate-card changes. Prices hold flat between changes because that is what a posted price does — no value here is interpolated.

CONTEXT
128,000
tokens

From OpenRouter's listing, read on 17 Nov 2026.

What it is good at
  • OCR & document understanding
  • Diagram and chart interpretation
  • Multi-image reasoning
  • Visual question answering
Typical use cases
  • Document Q&A
  • Receipt/form extraction
  • Chart-to-data
  • Accessibility descriptions

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from Qwen

See all 22 →

Price history

2 recorded changes
Recorded price changes for Qwen2.5 VL 72B Instruct, newest first
DateRateWasNowChange
8 Nov 2026Input$0.2500$0.8000+220%
8 Nov 2026Output$0.7500$1.00+33%

Rates per million tokens, as published by the provider or its router listing. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.

Frequently asked questions

How much does Qwen2.5 VL 72B Instruct cost?

Qwen2.5 VL 72B Instruct costs $0.8000 per million input tokens and $1.00 per million output tokens, for a blended reference rate of $0.8600 per million tokens.

What is Qwen2.5 VL 72B Instruct's context window?

Qwen2.5 VL 72B Instruct supports up to 128,000 tokens of context in a single request.

What is Qwen2.5 VL 72B Instruct best for?

Qwen2.5 VL 72B Instruct is well suited to OCR & document understanding, Diagram and chart interpretation and Multi-image reasoning.

Who makes Qwen2.5 VL 72B Instruct?

Qwen2.5 VL 72B Instruct is developed and served by Qwen.

Terms used on this page