Qwen: Qwen2.5 VL 72B Instruct
qwen/qwen2.5-vl-72b-instruct
JSONVision
Intelligence
—
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.800
210th cheapest
Context
128K
128K max out
How it compares
Cheaper than37%
of all ranked models
Overview
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.
Providers & pricing (2)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Nebiusfp8 | $0.250 | $0.750 | 32K | 99.2% |
| Parasailfp8 | $0.800 | $1.00 | 128K | 100% |
Specifications
Context window128K
Max output128K
Knowledge cutoffJun 2024
Input modalitiestext, image
Output modalitiestext
Prompt caching—
Cache read price$0.400/M
ModeratedNo
Open weightsQwen/Qwen2.5-VL-72B-Instruct ↗
Qwen2.5 VL 72B Instruct FAQ
How much does Qwen2.5 VL 72B Instruct cost?
Qwen2.5 VL 72B Instruct costs $0.800 per million input tokens and $1.00 per million output tokens via OpenRouter, making it 210th cheapest of 332 paid models.
What is Qwen2.5 VL 72B Instruct's context window?
Qwen2.5 VL 72B Instruct supports a 128K-token context window and can output up to 128K tokens. It accepts text, image input.
More from qwen
All Qwen2.5 VL 72B Instruct alternatives →Compare head-to-head
Qwen: Qwen2.5 VL 72B Instruct vs Qwen: Qwen3.7 FlashQwen: Qwen2.5 VL 72B Instruct vs Qwen: Qwen3.7 PlusQwen: Qwen2.5 VL 72B Instruct vs Qwen: Qwen3.7 MaxQwen: Qwen2.5 VL 72B Instruct vs Qwen: Qwen3.5 Plus 2026-04-20Qwen: Qwen2.5 VL 72B Instruct vs Qwen: Qwen3.6 FlashQwen: Qwen2.5 VL 72B Instruct vs Qwen: Qwen3.6 35B A3B