Qwen2.5-VL 72B Instruct pricing and specs
Qwen2.5-VL 72B Instruct pricing and specsQwen vision-language model for visual reasoning, documents, and agent tasks
Qwen2.5-VL 72B Instruct price per 1M tokens
| Type | ₽ / 1M | $ / 1M |
|---|---|---|
| Input tokens | 237 ₽ | $2.8 |
| Output tokens | 710 ₽ | $8.4 |
Prices in rubles as of 18.09.2026 at the CBR rate: 1 $ = 84.51 ₽.
Qwen2.5-VL 72B Instruct specs and limits
- Context window
- 131K
- Max output
- 8K
- Input
- text, image
- Output
- text
- Family
- qwen
- Released
- 2024-09-01
- Updated
- 2024-09-01
- Knowledge cutoff
- 2024-04
- Also known as
- qwen 2.5-vl 72b instruct, qwen3 2.5-vl 72b instruct, qwen 3 2.5-vl 72b instruct, qwen3.5 2.5-vl 72b instruct, qwen3.6 2.5-vl 72b instruct, qwen3.7 2.5-vl 72b instruct
What Qwen2.5-VL 72B Instruct can do
- —Reasoning
- ✓Tool calling
- —Structured output
- —Attachments / files
- ✓Vision (images)
- ✓Temperature control
- ✓Open weights
Model weights
Frequently asked questions
How much does the Qwen2.5-VL 72B Instruct API cost?
Input costs $2.8 per 1M tokens (237 ₽) and output costs $8.4 per 1M (710 ₽). Alibaba bills the prompt and the completion separately, so the price of a call depends on how long both are. Ruble figures use the Bank of Russia rate of 84.51 ₽ per dollar for September 2026.
How much do 1,000 Qwen2.5-VL 72B Instruct tokens cost?
List prices are quoted per 1M tokens, so 1,000 tokens cost a thousandth of that: divide $2.8 for input and $8.4 for output by 1,000. The same rates in rubles are 237 ₽ and 710 ₽ per 1M tokens. Both prompt tokens and completion tokens are billed.
How many tokens does Qwen2.5-VL 72B Instruct hold?
The Qwen2.5-VL 72B Instruct context window is 131K tokens (131,072). Everything shares that budget: the system prompt, the dialogue history, attached files and the answer the model writes. The figure comes from the Alibaba model card as of September 2026.
What are the Qwen2.5-VL 72B Instruct limits?
The context window is 131K tokens (131,072) and a single response is capped at 8K tokens, so longer output has to be generated in parts. Rate limits are set by Alibaba per account and depend on your plan rather than on the model, so they are not listed here.
How is the Qwen2.5-VL 72B Instruct price in rubles calculated?
Providers quote their tariffs in US dollars, so the ruble amounts here are a conversion at the official Bank of Russia rate of 84.51 ₽ per dollar. For Qwen2.5-VL 72B Instruct that gives 237 ₽ per 1M input tokens and 710 ₽ per 1M output tokens. When the rate moves, the ruble price moves with it.
How is Qwen2.5-VL 72B Instruct different from other Qwen models?
Qwen2.5-VL 72B Instruct belongs to the Qwen family at Alibaba. Models in the Qwen line differ in context size, price per 1M tokens and supported capabilities, so compare them by the numbers on their cards rather than by the name. Every Qwen model is listed on the provider page.
What capabilities does Qwen2.5-VL 72B Instruct support?
The declared capabilities of Qwen2.5-VL 72B Instruct are: tool calling, image input. It accepts text, images as input, and every attachment consumes tokens from the shared context window of 131K tokens. The list comes from the Alibaba model card and is refreshed with the catalog as of September 2026.
Does Qwen2.5-VL 72B Instruct have open weights?
Yes, Qwen2.5-VL 72B Instruct ships with open weights, so it can be downloaded and served on your own hardware instead of being used only through the Alibaba API. What you may do with it is set by the license shown on the card. Catalog prices cover hosted API access.