Qwen2.5 VL 72B Instruct API Pricing
Alibaba (Qwen) · context window 128K · prices updated 2026-09-20
Where Qwen2.5 VL 72B Instruct sits on price
At $1.00 per million output tokens, Qwen2.5 VL 72B Instruct is a mid tier model — 2.0× cheaper than the median output price of $2.00, which puts it cheaper than 69% and pricier than 31% of the models we track. It sits 23th cheapest of the 53 Alibaba (Qwen) models we track. Output is only 1.3× the input price, an unusually flat spread: long prompts hurt about as much as long answers, so prompt size is where the savings are.
Cached input is 50% cheaper. On an input-heavy workload you need roughly a 50% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.
What real workloads cost on Qwen2.5 VL 72B Instruct
These three workloads are the ones teams actually run on a mid-priced model — a $1.00/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. | $0.0054 | $81.00 |
| Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. | $0.0029 | $870 |
| Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. | $0.0006 | $16.50 |
Model your exact traffic in the API cost calculator — it preloads Qwen2.5 VL 72B Instruct with caching and batch options.
Qwen2.5 VL 72B Instruct price history
Alibaba (Qwen) last raised Qwen2.5 VL 72B Instruct's output price on Sep 4, 2026 (+33% per output token), from $0.25/$0.75 to $0.8/$1.00 per 1M in/out. That is one of 4 repricings in the 49 days we have tracked it — worth knowing before you hard-code today's rate into a budget.
| Date | Input /1M | Output /1M | Output change |
|---|---|---|---|
| Aug 2, 2026 (tracking began) | $0.8 | $1.00 | — |
| Aug 4, 2026 | $0.25 | $0.75 | -25% |
| Aug 17, 2026 | $0.8 | $1.00 | +33% |
| Aug 26, 2026 | $0.25 | $0.75 | -25% |
| Sep 4, 2026 | $0.8 | $1.00 | +33% |
Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).
Qwen2.5 VL 72B Instruct vs DeepSeek V3.1 Terminus
The closest-priced alternative from another vendor is DeepSeek V3.1 Terminus (DeepSeek) — priced within a rounding error on output, with $0.53 less per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See DeepSeek V3.1 Terminus pricing →Cheaper alternatives
More Alibaba (Qwen) models
Frequently asked questions
› How much does the Qwen2.5 VL 72B Instruct API cost?
Qwen2.5 VL 72B Instruct costs $0.8 per million input tokens and $1.00 per million output tokens, with cached input at $0.4 per million (50% cheaper). That works out to roughly 1,000,000 output tokens per dollar.
› What does the support chatbot workload cost on Qwen2.5 VL 72B Instruct?
Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0054 per request and $81.00 per month on Qwen2.5 VL 72B Instruct. Conversation history re-sent each turn — the classic prompt-caching win.
› What does it cost to fill Qwen2.5 VL 72B Instruct's 128K context window?
Sending 128K of input in a single request costs $0.1024 at $0.8 per million tokens — before any output. With prompt caching that same fill drops to about $0.0512 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.
› Is Qwen2.5 VL 72B Instruct worth the price?
Qwen2.5 VL 72B Instruct sits in the middle of the market (23 of 53 by price within Alibaba (Qwen)). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.