Alibaba Qwenopen weightsQwen2.5 VL 72B Instruct pricing
$0.80 per 1M input tokens and $1.00 per 1M output tokens. In real work that is 0.17¢ per chat answer and 1.3¢ to summarize a 20-page PDF.
What Qwen2.5 VL 72B Instruct costs per task
Token counts estimated from a measured model of the same lab (Qwen3.8 Flash), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.17¢$1.67 / 1,000 | 88 in · 689 out · 909 reasoning | 148 of 336 | estimated |
| Reply to a customer email | 0.09¢$0.95 / 1,000 | 326 in · 98 out · 587 reasoning | 167 of 336 | estimated |
| Write a 1,500-word blog post | ≥1.6¢$16.08 / 1,000 | 104 in · 0 out · 16,000 reasoning | 225 of 336 | estimated |
| Write 10 product descriptions | ≥1.6¢$16.28 / 1,000 | 345 in · 0 out · 16,000 reasoning | 257 of 336 | estimated |
| Translate 1,000 words | 0.24¢$2.41 / 1,000 | 1,386 in · 1,166 out · 136 reasoning | 114 of 336 | estimated |
| Proofread one page (500 words) | 0.25¢$2.45 / 1,000 | 777 in · 671 out · 1,159 reasoning | 169 of 336 | estimated |
| Summarize a 20-page PDF | 1.3¢$13.14 / 1,000 | 13,119 in · 501 out · 2,141 reasoning | 214 of 336 | estimated |
| Extract data from an invoice | 0.26¢$2.58 / 1,000 | 501 in · 561 out · 1,617 reasoning | 184 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥2.1¢$21.09 / 1,000 | 6,357 in · 0 out · 16,000 reasoning | 170 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.59¢$5.89 / 1,000 | 3,751 in · 974 out · 1,912 reasoning | 187 of 336 | estimated |
| Classify 100 support tickets | 0.96¢$9.58 / 1,000 | 1,463 in · 534 out · 7,879 reasoning | 204 of 336 | estimated |
| Review 500 lines of code | ≥2.0¢$19.90 / 1,000 | 4,874 in · 0 out · 16,000 reasoning | 205 of 336 | estimated |
| Write a SQL query | 0.28¢$2.77 / 1,000 | 177 in · 405 out · 2,225 reasoning | 189 of 336 | estimated |
| Run a 50-step coding agent | $1.03$1,033 / 1,000 | 2,259,875 in · 15,150 out · 80,850 reasoning | 237 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Qwen2.5 VL 72B Instruct through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 Parasailfp8 | $0.80 / $1.00 | $0.40 | 128K | 100% |
Price history
First seen in our price history on Mar 3, 2025 at $0.70 input / $0.70 output. Since then the output price moved from $0.70 to $1.00 per 1M tokens (16 changes).
FAQ
How much does Qwen2.5 VL 72B Instruct cost?
Qwen2.5 VL 72B Instruct costs $0.80 per 1 million input tokens and $1.00 per 1 million output tokens, with cached input at $0.40 (list price on Oct 18, 2026). In practice one chat answer costs about 0.17¢ and summarizing a 20-page PDF about 1.3¢.
Where is Qwen2.5 VL 72B Instruct cheapest?
Among 1 providers we track, the lowest list price today is at Parasail: $0.80 input and $1.00 output per 1M tokens.
Is the Qwen2.5 VL 72B Instruct cost per task measured or estimated?
Estimated: Qwen2.5 VL 72B Instruct was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Alibaba Qwen. Real usage can differ.