ModelBench
Alibaba Qwen logo
Models/Alibaba Qwen

Alibaba Qwen: Qwen2.5-VL 72B Instruct

Qwen vision-language model for visual reasoning, documents, and agent tasks

Source-linked qwen Open weights Released 2024-09
API record Report
InputT
OutputT
Input price$2.8/M
Output price$8.4/M
Context131.072K
Max output8.192K
Providers3
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Qwen2.5-VL 72B Instruct
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
DevPass (LLM Gateway) qwen2-5-vl-72b-instruct 32K 8.192K $0.25 $0.75 — Tools Docs ↗
Alibaba (China) qwen2-5-vl-72b-instruct 131.072K 8.192K $2.294 $6.881 — Tools Docs ↗
Alibaba qwen2-5-vl-72b-instruct 131.072K 8.192K $2.8 $8.4 — Tools Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.25/M

Across 3 priced providers

Median input $2.294/M

Midpoint of listed rates

Highest input $2.8/M

11.2× the lowest listed rate

Output range $0.75 – $8.4

Per million output tokens

DevPass (LLM Gateway) $0.25/MLowest
Alibaba (China) $2.294/M
Alibaba $2.8/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 32K to 131.072K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No
✓ Tool calling Yes
? Structured output Unknown
× Attachments No
✓ Vision input Yes
✓ Open weights Yes
Model family
qwen
Knowledge cutoff
2024-04
License
Not documented
Release date
2024-09
Model ID
alibaba/qwen2-5-vl-72b-instruct

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology
Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
Price Completion0.4 → 8.4
Price Prompt0.13 → 2.8
Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/alibaba/qwen2-5-vl-72b-instruct
curl
curl "https://model.kyssta.lol/api/v1/models/alibaba/qwen2-5-vl-72b-instruct"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Qwen2.5-VL 72B Instruct?

Qwen vision-language model for visual reasoning, documents, and agent tasks. It is published by Alibaba Qwen and catalogued here from Models.dev.

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

Listed input pricing starts at $0.25 per million tokens from DevPass (LLM Gateway), rising to $2.8 across 3 listed providers.

What is the context length of Qwen2.5-VL 72B Instruct?

Qwen2.5-VL 72B Instruct accepts up to 131.072K tokens of context and returns up to 8.192K output tokens.

Does Qwen2.5-VL 72B Instruct support tool calling and structured output?

Provider catalogs list support for tool calling, and image input.

Which providers serve Qwen2.5-VL 72B Instruct?

3 providers list this model: DevPass (LLM Gateway), Alibaba (China), Alibaba.

Are the weights for Qwen2.5-VL 72B Instruct open?

Yes. The weights are published and downloadable from Hugging Face.

When was Qwen2.5-VL 72B Instruct released?

The catalog records a release date of 2024-09, last verified Sep 11, 2026.

More models from Alibaba Qwen

View all →
Qwen2.5 72B Instruct

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

32.768K ctx $0.36/M in Qwen: Qwen3 VL 8B Instruct

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

131.072K ctx $0.117/M in Qwen: Qwen3.7 Max

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...

1M ctx $1.475/M in Qwen: Qwen3.6 35B A3B

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

262.144K ctx $0.1/M in