Qwen-VL Models by Alibaba
3 models2023Up to 32K ctxFrom $0.05/1M input
About
Qwen-VL is a family of 3 AI models by Alibaba, released in 2023.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
3 in view
Qwen-VLCurrent
Use when the workload needs 32K context and 7B parameters.
2023-1132K context7B parameters
Qwen-VL-PlusCurrent
Use when the workload needs 32K context, 72B parameters, and structured outputs.
2023-1132K context72B parametersstructured outputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Qwen-VL | Use when the workload needs 32K context and 7B parameters. | 2023-11 | 32K context7B parameters | Current |
| Qwen-VL-Plus | Use when the workload needs 32K context, 72B parameters, and structured outputs. | 2023-11 | 32K context72B parametersstructured outputs | Current |
| Qwen-VL-Max | Use when the workload needs structured outputs. | 2023-11 | structured outputs | Current |
Release Timeline
1 release group2023-11
3 current
Qwen-VL
Current32K context7B parameters
Qwen-VL-Max
Currentstructured outputs
Qwen-VL-Plus
Current32K context72B parametersstructured outputs
Specifications(3 models)
| Model | Released | Context | Parameters | Structured Outputs |
|---|---|---|---|---|
| Qwen-VL | 2023-11 | 32K | 7B | No |
| Qwen-VL-Plus | 2023-11 | 32K | 72B | Yes |
| Qwen-VL-Max | 2023-11 | — | — | Yes |
Available From(2 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Qwen-VL | Replicate API | $0.05 | $0.25 | Serverless |
| Qwen-VL-Plus | OpenRouter | $0.1365 | $0.4095 | Serverless |
| Qwen-VL-Max | OpenRouter | $0.52 | $2.08 | Serverless |
Frequently Asked Questions
- What is Qwen-VL used for?
- Qwen-VL is used for structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does Qwen-VL compare to Tongyi DeepResearch?
- Qwen-VL by Alibaba is strongest where you need structured outputs, while Tongyi DeepResearch by Alibaba is the closest related family to check for adjacent model selection. Qwen-VL has 3 listed variants and reaches up to 32K context, while Tongyi DeepResearch reaches up to 131K context, so compare the specs and pricing tables before choosing a production model.
- Which Qwen-VL model should I use?
- For the lowest listed input price, start with Qwen-VL through Replicate API at $0.05/1M input tokens. For the most capable/latest local choice, evaluate Qwen-VL-Plus with 32K context and structured outputs.