Qwen2.5-VL-72B-Instruct — Free AI Model & API

ovhcloud-ai-endpoints/qwen2-5-vl-72b-instruct

chat

Get API key →

Context Window 128K

Max Output 8K

Rate Limit 2 RPM (anonymous)

Cost $0.00 FREE

Free Period Since May 10, 2026

Credit Card Not required

Status Online

Overview

Qwen2.5 VL 72B is Alibaba's large vision-language model, available free on OVHcloud AI Endpoints. With 128K context, OpenAI-compatible API, and full multimodal support (text + vision), it is a strong choice for image understanding, visual Q&A, and document analysis with diagrams. The 8K output per request is sufficient for most vision tasks. Hosted on OVHcloud's European infrastructure; registration required.

Model ID

qwen2-5-vl-72b-instruct

Base URL

https://oai.endpoints.kepler.ai.cloud.ovh.net/v1

Specifications

Context: 128K · Output: 8K · Modality: text, image · OpenAI Compat: Yes

Quick Start

Integrate Qwen2.5-VL-72B-Instruct with 3 lines of code. See the config generator for Claude Code, Cursor, and more.

from openai import OpenAI

client = OpenAI(
 base_url="https://oai.endpoints.kepler.ai.cloud.ovh.net/v1",
 api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
 model="qwen2-5-vl-72b-instruct",
 messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const openai = new OpenAI({
 baseURL: "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1",
 apiKey: "YOUR_API_KEY",
});

const completion = await openai.chat.completions.create({
 model: "qwen2-5-vl-72b-instruct",
 messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);

curl https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer YOUR_API_KEY" \
 -d '{
 "model": "qwen2-5-vl-72b-instruct",
 "messages": [{"role": "user", "content": "Hello!"}]
 }'

Other Free Models from OVHcloud AI Endpoints

Meta-Llama-3_3-70B-Instruct

131K context · No card

DeepSeek-R1-Distill-Llama-70B

131K context · No card

Qwen3-Coder-30B-A3B-Instruct

262K context · No card

Mistral-Nemo-Instruct-2407

128K context · No card

Qwen3Guard-Gen-8B

32K context · No card

Rate Limits & Constraints

Rate Limit 2 RPM (anonymous)

Context Window 128K

Max Output Tokens 8K

Cost Free — since May 10, 2026

Credit Card Not required

OpenAI Compatible Yes — drop-in replacement

OVHcloud AI Endpoints Platform Limitations

Anonymous tier has very low, unpublished rate limits
Some models experience cold starts (5-10s first request)
EU-hosted only — higher latency outside Europe

Features & Use Cases

Best For

Chat

Modality Support

textimage

OVHcloud AI Endpoints Highlights

No registration needed for anonymous tier
EU-hosted (GDPR compliant)
Qwen3-Coder, Mistral, Llama, DeepSeek
OpenAI-compatible endpoint

Playground — Test Qwen2.5-VL-72B-Instruct

Test Qwen2.5-VL-72B-Instruct directly in your browser. Your API key is sent directly to OVHcloud AI Endpoints — never stored.

Model: Qwen2.5-VL-72B-Instruct Get Key

🔒 Your key is never stored — sent directly to the model provider via our server proxy.

Ready to chat with Qwen2.5-VL-72B-Instruct.

Frequently Asked Questions

How do I get an API key for Qwen2.5-VL-72B-Instruct?

Sign up at OVHcloud AI Endpoints to get your API key. No credit card is required — just an email sign-up. Once you have the key, use the code snippets in the Quick Start section above.

Is Qwen2.5-VL-72B-Instruct really free?

Yes. Qwen2.5-VL-72B-Instruct is available on OVHcloud AI Endpoints's free tier and has been free since May 10, 2026. Rate limits apply: 2 RPM (anonymous). Always check the provider's terms for any changes to the free tier.

What are Qwen2.5-VL-72B-Instruct's rate limits?

2 RPM (anonymous) Context window: 128K. Max output: 8K. No credit card required.

What are the best free alternatives to Qwen2.5-VL-72B-Instruct?

Popular free alternatives include inclusionAI: Ring-2.6-1T, Baidu Qianfan: CoBuddy (free), Owl Alpha. You can also browse all 147+ free models on our site.