Alex Getmanearly AI signals

Qwen2.5 VL 72B Instruct

Alibaba

ReleasedUpdated
Context window
33K
32,768 tokens
Input / Output
image, text → text

API pricing

USD / 1M tokens

InputOutputCached input
  • $0.80
openrouter
  • $1.00
openrouter
  • $0.40
openrouter

Timeline

  1. · Weights version · evidence link
Input / output price · USD / 1M tokens
ModelEvidence linksInput / output price
qwen/qwen2.5-vl-72b-instruct
standard
openrouter$0.80 / $1.00
Specifications

Qwen2.5 VL 72B Instruct is a model from Alibaba with open weights, first recorded on 30 Sep 2026; its release date is not established. The context window is 32,768 tokens. Pricing is $0.80 per million input tokens and $1.00 per million output tokens.

Context window
32,768
Input
image · text
Output
text
Weights
Open
Input · USD / 1M tokens
$0.80
Output · USD / 1M tokens
$1.00
Cached input · USD / 1M tokens
$0.40

Questions

What is the context window of Qwen2.5 VL 72B Instruct?

The context window is 32,768 tokens.

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

Pricing is $0.80 per million input tokens and $1.00 per million output tokens. Cached input is $0.40 per million.

Are the weights of Qwen2.5 VL 72B Instruct publicly available?

Yes. Alibaba publishes the weights.

When was Qwen2.5 VL 72B Instruct released?

Its release date is not established. Signal Forge first recorded it on 30 Sep 2026.