Qwen2.5 VL 72B pricing
$$ Standard$0.80/M input · $1.00/M output. List prices from provider data; in idapt, chat is metered per token with transparent, usage-based pricing at the prices shown in the app.
Full rate table
| Rate | Price | Unit |
|---|---|---|
| Input | 0.7999999999999999 | /M tokens |
| Output | 1 | /M tokens |
| Cache read | 0.39999999999999997 | /M tokens |
What typical work costs
| Workload | Tokens | List price |
|---|---|---|
| Quick question | 1K tokens in, 500 out | $0.0013 |
| Long-document summary | 60K tokens in, 2K out | $0.05 |
| Agent working session | 400K tokens in, 40K out across a day | $0.36 |
Price your own workload
- Per call
- $0.0013
- Per month
- $0.13
Compare up to four models at once in the cost calculator.
Frequently asked
What does Qwen2.5 VL 72B cost per 1M tokens?
Qwen2.5 VL 72B lists at $0.80 per 1M input tokens and $1.00 per 1M output tokens.
Does Qwen2.5 VL 72B discount cached input tokens?
Yes. Cached input tokens are billed at $0.40 per 1M, versus $0.80 for fresh input. Prompts that repeat a long prefix (a system prompt, attached files) benefit the most.
What does a typical chat message with Qwen2.5 VL 72B cost?
A message with about 1,000 input tokens and a 500-token reply costs roughly $0.0013 at list price. Long documents and long replies scale that linearly with token counts.
Is Qwen2.5 VL 72B cheaper than Qwen2.5 72B?
Qwen2.5 72B has the lower blended price at a 3:1 input:output mix. Qwen2.5 VL 72B: $0.80 in / $1.00 out per 1M. Qwen2.5 72B: $0.36 in / $0.40 out per 1M.
How does idapt bill Qwen2.5 VL 72B?
Chat with Qwen2.5 VL 72B in idapt is metered per token with transparent, usage-based pricing at the prices shown in the app. Subscriptions include a weekly usage allowance before any balance is touched.
Part of the Qwen2.5 VL 72B model page · cheapest models board · price changes