Alibaba (Qwen) · Released Oct 28, 2024Qwen-VL OCR
OCR model for extracting structured text from documents and screenshots.
- Capability
- —No ECI score yet
- Input
- $0.72per 1M tokens
- Output
- $0.72per 1M tokens
- Context
- 34K4K max output
What it costs
- Input
- $0.72per million tokens
- Output
- $0.72per million tokens
- Blended (3:1)
- $0.72cheaper than 52% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $1.80 |
| Team assistant25M input + 5M output tokens | $21.60 |
| Production app250M input + 50M output tokens | $216.00 |
Official Alibaba API price, as listed on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Qwen-VL OCR yet.
The details
- Lab
- Alibaba (Qwen)
- Released
- Oct 28, 2024
- Knowledge cutoff
- Apr 2024
- Context window
- 34,096 tokens
- Max output
- 4,096 tokens
- Inputs
- Text, Images
- Output
- Text
- Reasoning
- No
- Tool calling
- No
- Structured output
- No
- Weights
- Proprietary
- API model ID
qwen-vl-ocron Alibaba- Availability
- 1 API providerlisted on models.dev
More from Alibaba (Qwen)
About Qwen-VL OCR
How much does Qwen-VL OCR cost?
Qwen-VL OCR costs $0.72 input / $0.72 output per million tokens (official Alibaba API price). At a 3:1 input-to-output mix that is $0.72 per million tokens, cheaper than 52% of the 360 priced models we track.
What is the context window of Qwen-VL OCR?
Qwen-VL OCR accepts up to 34,096 tokens per request and can write up to 4,096 tokens in one response.
How good is Qwen-VL OCR?
Epoch AI has not published a Capabilities Index score for Qwen-VL OCR yet.
Is Qwen-VL OCR open source?
No. Qwen-VL OCR is proprietary; you use it through Alibaba’s API or partner platforms.
What inputs does Qwen-VL OCR support?
Qwen-VL OCR accepts text and images and replies in text. It is not a dedicated reasoning model, does not support tool calling.
When was Qwen-VL OCR released?
Alibaba (Qwen) released Qwen-VL OCR on Oct 28, 2024. Its training data runs to Apr 2024.
What are the best alternatives to Qwen-VL OCR?
The closest current models from other labs on capability, price and release date are Aya Expanse 32B (Cohere, $0.50 / $1.50), Llama 3.1 Nemotron 70B Instruct (NVIDIA, $0.478 / $0.504), Codestral (Mistral AI, $0.30 / $0.90) and Llama-3.2-11B-Vision-Instruct (Meta, $0.197 / $0.51).