Alibaba Qwen · 2025-02-01
Qwen2.5 VL 72B Instruct pricing
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects.
Prices from OpenRouter’s models API, updated October 29, 2026
What Qwen2.5 VL 72B Instruct costs a month
| Workload | Standard |
|---|---|
| Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out | $48.00 |
| Daily summaries: 10,000 a day, 3,000 tokens in, 300 out | $810 |
| Coding agent: 400 calls a day, 60,000 tokens in (80% cached), 2,000 out | $370 |
30 days. Cached input billed at the cache-read price. Use your own numbers.
Cheaper models with a similar context window
| Model | Provider | Input /1M | Output /1M | Cache read /1M | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|
| Extract | scaledown | $0.04 | $0 | – | 1M | $1.80 |
| Summarize | scaledown | $0.04 | $0 | – | 1M | $1.80 |
| Nex-N2.5-Mini | nex-agi | $0.025 | $0.10 | $0.0025 | 262K | $2.33 |
| GLM 5.3 Flash | Z.ai | $0.046 | $0.074 | $0.03 | 1.05M | $2.95 |
| Qwen3.7 Flash | Alibaba Qwen | $0.03 | $0.13 | $0.006 | 1M | $2.91 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
Cheaper isn’t automatically as good. Glow’s GlowBench scores models on your kind of task before suggesting a swap.
Other Qwen models
| Model | Input /1M | Output /1M | Cache read /1M | Context | Chatbot, per month* |
|---|---|---|---|---|---|
| Qwen3.8 Max Prime | $4 | $12 | $0.50 | 1M | $324 |
| Qwen3.8 Omni Flash | $0.15 | $0.47 | $0.016 | 1M | $12.39 |
| Qwen3.8 Max (0902) | $2 | $6 | $0.25 | 1M | $162 |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | 1M | $12.39 |
| Qwen3.8 27B | $0.039 | $1.25 | $0.0039 | 1M | $16.75 |
| Qwen3.8 2.4T A95B | $2 | $6 | $0.25 | 1.05M | $162 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
Related
Qwen2.5 VL 72B Instruct: questions
How much does Qwen2.5 VL 72B Instruct cost?
$0.80 per 1M input tokens and $1 per 1M output tokens, with cached input at $0.40. A 1,000-token prompt with a 500-token answer costs about $0.0013.
What is Qwen2.5 VL 72B Instruct’s context window?
128,000 tokens, with up to 115,200 output tokens per response.
Is there a cheaper alternative to Qwen2.5 VL 72B Instruct?
Extract costs $0.04 in and $0 out per 1M tokens with a similar context window. Whether it matches Qwen2.5 VL 72B Instruct’s quality depends on the task: test it on your own prompts (Glow’s GlowBench does this per task).
Know what each model really costs you.
Connect OpenRouter and Glow shows spend by model, key and product, and flags the swap that saves the most at the same quality.
- Read-only keys
- Never shown again
- 2FA + Face ID
- 7-day trial