Models
Price comparison

Qwen2.5-VL 72B Instruct

Qwen2.5-VL 72B Instruct by Alibaba Cloud: 4 offers. From €0.72 per 1M input tokens, with EU processing from €0.91.

Calculate costs for this modelCompare offersView price history

Profile

Profile
DeveloperAlibaba Cloud
TypeImage models
OriginCN
Input typestext+bild
Context (tokens)128,000
Max. output (tokens)–
Reasoning–
Parameters (bn)73.41
Open weights✓ yes
LicenceQwen-Lizenz (nicht Apache)
VRAM at 4-bit (GB)45 (RTX PRO 5000)
Released–

Offers with processing in the EU (2)

ProviderCountryVariantInputOutputSourceAs of
cortecsATstandard€0.91€0.91api.cortecs.ai14 Oct 2026
OVHcloudFRstandard€0.91€0.91www.ovhcloud.com13 Oct 2026

€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.

Offers outside the EU (2)

ProviderCountryVariantInputOutputSourceAs of
ParasailUSstandard€0.72€0.89www.parasail.io2 Oct 2026
ParasailUSserverless€0.72€0.89www.parasail.io2 Oct 2026

€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.

AI Act

Whether the developer has signed the Code of Practice for general-purpose AI models: unknown. What this means is explained under “EU and AI Act”. EU processing and AI Act

Benchmarks

Benchmarks
HallusionBench (llm-stats-Abzug)0.55
MMMU-Pro (llm-stats-Abzug, Rang 1..50 von 69)0.51
OCRBench v2, englische Spur (llm-stats-Abzug)0.61

Report an error on this page