Qwen2.5-VL 72B Instruct pricing, context window and limits
Qwen2.5-VL 72B Instruct costs $2.294 per million input tokens and $6.881 per million output tokens at Alibaba Qwen list price. It accepts up to 131,072 tokens of context and returns up to 8,192 tokens.
- Model id
qwen2-5-vl-72b-instruct - Snapshot
What does Qwen2.5-VL 72B Instruct cost?
| Input | $2.294 |
|---|---|
| Output | $6.881 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Qwen2.5-VL 72B Instruct read and write?
| Context window | 131,072 |
|---|---|
| Max output | 8,192 |
What can Qwen2.5-VL 72B Instruct do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | No |
| Reasoning | No |
| Input | text, image |
| Output | text |
What does a request to Qwen2.5-VL 72B Instruct cost?
| A typical request: 1,000 tokens in, 500 out | $0.0057 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.03 |
| 1,000 typical requests | $5.73 |
| 1 million tokens in and 1 million out | $9.18 |
Among 64 Alibaba Qwen models with a published price, Qwen2.5-VL 72B Instruct is the 62nd cheapest by input price. Its context window is the 24th largest of 64. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Qwen2.5-VL 72B Instruct through DVARA?
Configure the qwen provider in the DVARA LLM Gateway and send the model id qwen2-5-vl-72b-instruct. DVARA, the AI governance platform, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set is counted as costing nothing. Every cost record says which price it used.
Which other Alibaba Qwen models are there?
- Qwen2.5-Omni 7B$0.087 in · $0.345 out · 33K context
- Qwen2.5-VL 7B Instruct$0.287 in · $0.717 out · 131K context
- Qwen2.5-Math 7B Instruct$0.144 in · $0.287 out · 4K context
- Qwen2.5-Math 72B Instruct$0.574 in · $1.721 out · 4K context
- Qwen2.5-Coder 7B Instruct$0.144 in · $0.287 out · 131K context
- Qwen2.5-Coder 32B Instruct$0.287 in · $0.861 out · 131K context
- Qwen2.5 7B Instruct$0.072 in · $0.144 out · 131K context
- Qwen2.5 72B Instruct$0.574 in · $1.721 out · 131K context
- Qwen2.5 32B Instruct$0.287 in · $0.861 out · 131K context
- Qwen2.5 14B Instruct$0.144 in · $0.431 out · 131K context
- Qwen3 14B$0.144 in · $0.574 out · 131K context
- Qwen3 235B-A22B$0.287 in · $1.147 out · 131K context
Which models from other providers are similar to Qwen2.5-VL 72B Instruct?
These are the closest in context window and input price, one per provider.
- Command A PlusCohere · $2.5 in · $10 out · 128K context
- GPT-4oOpenAI · $2.5 in · $10 out · 128K context
- Deep Research Max Preview (Apr-21-2026)Google Gemini · $2 in · $12 out · 131K context
- Mistral Large 2.1Mistral AI · $2 in · $6 out · 131K context
- Palmyra X4 (US)Amazon Bedrock · $2.5 in · $10 out · 123K context