Skip to content
LLMs
Qwen logo

Qwen: Qwen2.5 VL 72B Instruct

by Qwen

Qwen: Qwen2.5 VL 72B Instruct is a large language model from Qwen. It costs $0.800 per million input tokens and $1.00 per million output tokens. Its context window is 128K tokens.

Structured outputPrompt cachingOpen weightsimage input
Input / 1M tokens
$0.800
Output / 1M tokens
$1.00
Cached input / 1M
$0.400

On repeated prefixes

Context window
128K

tokens

Who serves it cheapest

1 hosts serve Qwen2.5 VL 72B Instruct. Same weights, same API - the price difference is pure margin and routing.

Providers serving Qwen: Qwen2.5 VL 72B Instruct, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
ParasailCheapestfp8$0.800$1.00128K-100.0%

About Qwen2.5 VL 72B Instruct

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.

Specifications

Qwen: Qwen2.5 VL 72B Instruct specifications
Model IDqwen/qwen2.5-vl-72b-instruct
ProviderQwen
Context window128K tokens
Max output115K tokens
Input modalitiestext, image
Output modalitiestext
Knowledge cutoff2024-06-30
Open weightsYes - Qwen/Qwen2.5-VL-72B-Instruct
ReleasedFebruary 1, 2025

Cheaper alternatives

Models that cost less than Qwen2.5 VL 72B Instruct while keeping at least half its context window and every input modality it supports.

Frequently asked

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

$0.800 per million input tokens and $1.00 per million output tokens. Cached input reads cost $0.400 per million tokens.

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

128K tokens, with up to 115K tokens of output per request.

Confirm against the source: Qwen official pricing.