Qwen2.5-VL 72B Instruct: API pricing, providers and specs
Qwen2.5-VL 72B Instruct is a text model by Alibaba. 5 providers serve it, from $0.50 to $1.02 /1M; the lowest price is at AIHubMix.
How Qwen2.5-VL 72B Instruct compares
Against the 737 text models on the site priced the same way.
- Mid-priced: its lowest price is $0.50 /1M against a median of $1.10; 34% of comparable models cost less.
- Its 128K-token context window is larger than 12% of them (median 262K), about 190 pages of text.
- On LMArena's Vision board it ranks #3 of the 8 comparable models scored there.
- 5 providers serve it; 65% of comparable models have fewer.
- Its weights are open under the qwen license: commercial use under the maker's terms.
Qwen2.5-VL 72B Instruct prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 AIHubMix | $0.50/1M | From$0.50/1M | — | — |
 Jiekou.AI | $0.80/1M | $0.80/1M | — | — |
| OpenRouter | $0.80/1M | From$1/1M | $0.40/1M | 128K |
 Hugging Face | $1.01/1M | From$1.01/1M | — | — |
 Cortecs | $1.02/1M | $1.02/1M | — | — |
- AIHubMixFrom$0.50
- Jiekou.AI$0.80
- OpenRouterFrom$1
- Hugging FaceFrom$1.01
- Cortecs$1.02
Specs
- Type
- Text
- Maker
- Alibaba
- Inputs
- Image, Text
- Outputs
- Text
- Context
- 128K≈ 190 pages of text
- Max output
- 115K
- Capabilities
- Prompt caching, JSON, Vision
- Released
- Jan 27, 2025
- License
- qwencommercial use under the maker's terms
- Open weights
- Yes, downloadable
- Parameters
- 73B
- Arena score
- 1107Vision
Alternatives to Qwen2.5-VL 72B Instruct
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Qwen2.5-VL 72B Instructthis model | $0.50/1M | 128K | 1107 | 5 |
 GLM-5.3 | $1.10/1M | 1.05M | 1623 | 49 |
| GLM-5.3-Flash | $0.20/1M | 1.05M | 1608 | 45 |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
 Sonar | $1/1M | 127K | — | 9 |
| Claude Haiku 5.5 | $0.30/1M | 1M | 1585 | 27 |
 MiMo-V2.6-Pro | $0.696/1M | 1.05M | 1625 | 21 |
 DeepSeek V4 Flash | $0.17/1M | 1.05M | — | 26 |
| DeepSeek V4 Flash Vision Exp | $0.294/1M | 1.05M | — | 26 |
More from Alibaba
Qwen-Image-2.1Alibaba$0.02/imgQwen3.8 2.4T A95BAlibaba$4.11/1MWan3.0Alibaba$0.025/secQwen3.8 27BAlibaba$0.50/1MWan 2.2Alibaba$0.01/runQwen3.8 Flash NextAlibaba$0.376/1MQwen2-1.5B-InstructAlibaba$0.20/1MQwen3.5 FlashAlibaba$0.287/1MQwen2.5-VL 72B Instruct FAQ
The lowest price for Qwen2.5-VL 72B Instruct is $0.50 /1M, at AIHubMix.
AIHubMix, at $0.50 /1M. 5 providers serve Qwen2.5-VL 72B Instruct; the table above lists every one with its price.
Qwen2.5-VL 72B Instruct reads up to 128K tokens per request and writes up to 115K.
Yes. Qwen2.5-VL 72B Instruct's weights can be downloaded from its maker's Hugging Face page, under the qwen license.
About 73B, as the safetensors metadata of its official Hugging Face repo states.
5 API providers serve Qwen2.5-VL 72B Instruct. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us