Models · Qwen

Qwen2.5-VL 72B, paused on Evanesca.

Qwen2.5-VL 72B is an open-weight model by Qwen built to read images, released under the Qwen License Agreement. Paused since 20 Oct 2026: OVHcloud, the only European operator that runs it for Evanesca, is not serving it at the moment. Meanwhile, pick Pixtral 12B or Qwen3.6 35B.

Checked on 20 Oct 2026

Qwen2.5-VL 72B

by Qwen · Qwen License Agreement

Gravelines, France Checks 5/6

Input / M: €1.5288
Output / M: €1.5288
Quick question: €0.0011

Prices per million tokens, VAT included. Quick question: 300 tokens in, 400 out.

The model at a glance

Maker: Qwen
Licence: Qwen License Agreement
Size: 73.4B parameters
Context: 32k tokens as the operator announces it
Type: Vision
Tool calling: No measured by a real call
Reasoning: —
Run by: OVHcloud OVH SAS, France — no US parent company Paused since 20 Oct 2026
Where it runs: Gravelines, France
Checks: 5/6 · Security ✕ Passed: Licence, Provenance, GDPR, Benchmarks and Live test
Price: €1.5288 per million input tokens · €1.5288 per million output tokens VAT included; reasoning tokens count as output
Open weights: Yes published by the maker: an operator can run the model
Model card: huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct

Where your prompts go

Here is the route of a message sent to Qwen2.5-VL 72B, end to end. No call to the model leaves Europe: not as a backup, not when servers are busy.

From your browser to EvanescaEvanesca passes your message straight on to OVHcloud. It stores neither the prompt nor the answer: both stay in memory only while the answer is written.
OVHcloud, GravelinesWhen it is served: OVHcloud runs Qwen2.5-VL 72B in Gravelines, France. It is a French company with no US parent: out of the CLOUD Act's direct reach. OVHcloud states “zero data retention: we keep only the data required for billing purposes” (OVHcloud AI Endpoints).
Back to you, with its passportThe answer comes back with its passport: model, operator, country, and what was kept. Your history lives in your browser; about this message, Evanesca keeps only billing data — tokens and cost.

What it costs

€1.5288 per million input tokens and €1.5288 per million output tokens, VAT included. Three typical exchanges on Qwen2.5-VL 72B:

COST OF AN EXCHANGE · VAT INCLUDED
Example	Tokens in	Tokens out	Cost
A quick question	300	400	€0.0011
A long document to summarise	15,000	800	€0.0242
A message late in a long conversation	40,000	2,000	€0.0642

€2 of credit covers about 1,800 quick questions on this model. Reasoning tokens count as output, so a model that thinks first can cost more than these examples. The exact cost of each answer shows under it. All prices.

Licence

Qwen publishes Qwen2.5-VL 72B under the Qwen License Agreement. Qwen's own licence, not Apache-2.0: a product with more than 100 million monthly active users must ask Qwen for a licence (licence text).

The official model card is the reference.

Similar models

Same maker first, then the same type.

Paris, France

Qwen3.8 27B

Qwen · Text + images · checks 6/6

€1.008 · €5.544 / M tokens

Paris, France

Qwen3.6 35B

Qwen · Text + images · checks 6/6

€0.42 · €2.52 / M tokens

Paris, France

Qwen3.5 397B

Qwen · Text + images · checks 6/6

€1.008 · €6.048 / M tokens

Paris, France

Qwen3 Coder 30B

Qwen · Code · checks 5/6

€0.336 · €1.344 / M tokens

Paris, France

Qwen3 235B

Qwen · Text · checks 5/6

€1.26 · €3.78 / M tokens

Paris, France

Pixtral 12B

Mistral AI · Vision · checks 5/6

€0.336 · €0.336 / M tokens

Every model, with its operator and where it runs

Frequently asked questions

Can I use Qwen2.5-VL 72B today?

Not at the moment: it has been paused since 20 Oct 2026, because OVHcloud, the only European operator that runs it for Evanesca, is not serving it for now. A call answers 503 and is not billed. Meanwhile, use Pixtral 12B or Qwen3.6 35B.

Where does Qwen2.5-VL 72B run on Evanesca?

When it is served: In Gravelines, France, on OVHcloud's servers. OVHcloud is a French company with no US parent, so your prompts stay out of the CLOUD Act's direct reach. No call to the model leaves Europe: not as a backup, not when servers are busy.

Does Evanesca keep what I send to Qwen2.5-VL 72B?

No. The prompt and the answer stay in memory only while the answer is written, and your history lives in your browser; about your messages, Evanesca keeps only billing data — tokens and cost. OVHcloud states “zero data retention: we keep only the data required for billing purposes” (OVHcloud AI Endpoints).

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

€1.5288 per million input tokens and €1.5288 per million output tokens, VAT included. A quick question — 300 tokens in, 400 out — costs about €0.0011. There is no subscription: credit starts at €2.

Can Qwen2.5-VL 72B call tools?

No: a real call showed that OVHcloud refuses tool calls for this model.

Which licence is Qwen2.5-VL 72B under?

Qwen License Agreement. Qwen's own licence, not Apache-2.0: a product with more than 100 million monthly active users must ask Qwen for a licence (licence text).

Which checks has Qwen2.5-VL 72B passed?

5 of 6: Licence, Provenance, GDPR, Benchmarks and Live test. Missing: Security — not checked yet, or checked without meeting the pass mark. Its passport shows the same stamps; how each check works.

Does Qwen see what I type?

No. Qwen published the weights, and OVHcloud runs them in France: your prompts go to OVHcloud's servers, not to Qwen.