Models/Qwen/Qwen2.5 VL 72B Instruct

Qwen2.5 VL 72B Instruct

Name: Qwen2.5 VL 72B Instruct API access
Brand: Qwen

Qwen · Open weights · Released Feb 1, 2025 · qwen/qwen2.5-vl-72b-instruct

Compare Estimate cost

128K contextVisionStructured outputPrompt cachingOpen weights

Available from 2 providersUSD / MTOK · VERIFIED 4 MINUTES AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
Nebius	$0.25	$0.75	—	32K	fp8	2.4s	36 tok/s	97.8%
Parasail	$0.80	$1.00	$0.40	128K	fp8	1.4s	50 tok/s	99.9%

TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 44 hours ago

About

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

Context window128,000

Max output128,000

Modalities intext, image

Modalities outtext

LicenseOpen weights

ReleasedFeb 1, 2025

Knowledge cutoff2024-06-30

TokenizerQwen

WeightsHugging Face ↗

Open weights

Hugging FaceQwen/Qwen2.5-VL-72B-Instruct ↗

Downloads273.1K

Likes650

Licenseother

safetensors

Qwen3.8 27B$0.35 / $2.55 Qwen3.8 2.4T A95B$2.00 / $6.00 Qwen3.8 Max$2.00 / $6.00 Qwen3.7 Flash$0.03 / $0.13

Embed badge

Qwen2.5 VL 72B Instruct price and speed badge

[![Qwen2.5 VL 72B Instruct](https://modelindex.ai/badge/qwen/qwen2.5-vl-72b-instruct)](https://modelindex.ai/models/qwen/qwen2.5-vl-72b-instruct)

Sources

OpenRouter API4 minutes ago

AGGREGATOR

Hugging Face4 minutes ago

COMMUNITY

ModelIndex benchmarks44 hours ago

MEASURED

Verified 4 minutes ago · list prices, not negotiated rates.