Skip to main content
OpenRouter logo

Qwen 2.5 VL 72B API pricing on OpenRouter

Every OpenRouter Qwen 2.5 VL 72B rate we track, compared against 4 providers serving the same model.

Input from /1M
$0.800
Output /1M
$1.00
Input price rank
#2 of 4
Last updated
November 21, 2026

The cheapest Qwen 2.5 VL 72B input price we currently track is $0.700/1M on Liquid Inference.

The cheapest Qwen 2.5 VL 72B output price is $0.700/1M on Liquid Inference.

OpenRouter Qwen 2.5 VL 72B rates

Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.

OpenRouter Qwen 2.5 VL 72B pricing by mode
ModeInputOutput
Standard$0.800/1M$1.00/1M

About Qwen 2.5 VL 72B

Creator
Alibaba
Context
128K
Modalities
text, image
Tool calling
Yes
Open weights
Yes
Full Qwen 2.5 VL 72B details and every provider →Compare API pricing for every Qwen model →

Qwen 2.5 VL 72B on other providers

About OpenRouter

OpenRouter provides a unified API for accessing hundreds of AI models from multiple providers. It aggregates models from OpenAI, Anthropic, Google, Meta, Mistral, and many others, offering a single endpoint with automatic fallback routing and provider optimization.

Frequently Asked Questions

How much does Qwen 2.5 VL 72B cost on OpenRouter?

OpenRouter serves Qwen 2.5 VL 72B from $0.800 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.

Is OpenRouter the cheapest way to run Qwen 2.5 VL 72B?

OpenRouter ranks #2 of 4 providers we track serving Qwen 2.5 VL 72B on input price. The cheapest input price right now is on Liquid Inference. The lowest output price is $0.700/1M on Liquid Inference. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does OpenRouter offer batch or cached pricing for Qwen 2.5 VL 72B?

We track 1 Qwen 2.5 VL 72B offering from OpenRouter. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.