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

Best $0.80 in / $1.00 out via Parasail · fp8

Compare Estimate cost

128K contextVisionStructured outputPrompt cachingOpen weights

Available from 1 providerUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 2 MINUTES AGO

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

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
Parasail	$0.80	$1.00	$0.40	128K	fp8	1.4s	46 tok/s	100.0%

TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 2 minutes ago

SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →

Pricing variants · USD / MTok in / out

STANDARD

$0.80 / $1.00

per MTok in / out

CACHE READ $0.40

Recent changesRSS ↗

Sep 4, 2026endpoint removed · nebius2 → 1

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 output115,200

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 ↗

Downloads68.9K

Likes659

Licenseother

safetensors

Qwen3.8 Max Prime$4.00 / $12.00 Qwen3.8 Omni Flash$0.15 / $0.47 Qwen3.8 Max (0902)$2.00 / $6.00 Qwen3.8 Flash$0.15 / $0.47

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 API23 minutes ago

AGGREGATOR

Hugging Face23 minutes ago

COMMUNITY

ModelIndex benchmarks2 minutes ago

MEASURED

Verified 23 minutes ago · list prices, not negotiated rates.