Qwen-VL OCR pricing, context window and limits
Qwen-VL OCR costs $0.043 per million input tokens and $0.072 per million output tokens at Alibaba Qwen list price. It accepts up to 34,096 tokens of context and returns up to 4,096 tokens.
- Model id
qwen-vl-ocr - Snapshot
What does Qwen-VL OCR cost?
| Input | $0.043 |
|---|---|
| Output | $0.072 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Qwen-VL OCR read and write?
| Context window | 34,096 |
|---|---|
| Max output | 4,096 |
What can Qwen-VL OCR do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | No |
| Structured output | No |
| Reasoning | No |
| Input | text, image |
| Output | text |
What does a request to Qwen-VL OCR cost?
| A typical request: 1,000 tokens in, 500 out | under $0.0001 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0005 |
| 1,000 typical requests | $0.079 |
| 1 million tokens in and 1 million out | $0.12 |
Among 64 Alibaba Qwen models with a published price, Qwen-VL OCR is the 6th cheapest by input price. Its context window is the 50th largest of 64. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Qwen-VL OCR through DVARA?
Configure the qwen provider in the DVARA LLM Gateway and send the model id qwen-vl-ocr. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Alibaba Qwen models are there?
- Qwen-VL Max$0.23 in · $0.574 out · 131K context
- Qwen-VL Plus$0.115 in · $0.287 out · 131K context
- Qwen Turbo$0.044 in · $0.087 out · 1M context
- Qwen Plus Character$0.115 in · $0.287 out · 33K context
- Qwen Plus$0.115 in · $0.287 out · 1M context
- Qwen-Omni Turbo Realtime$0.23 in · $0.918 out · 33K context
- Qwen-Omni Turbo$0.058 in · $0.23 out · 33K context
- Qwen-MT Turbo$0.101 in · $0.28 out · 16K context
- Qwen-MT Plus$0.259 in · $0.775 out · 16K context
- Qwen Max$0.345 in · $1.377 out · 131K context
- Qwen Math Turbo$0.287 in · $0.861 out · 4K context
- Qwen Math Plus$0.574 in · $1.721 out · 4K context
Which models from other providers are similar to Qwen-VL OCR?
These are the closest in context window and input price, one per provider.
- Voxtral Mini 3B 2507Amazon Bedrock · $0.04 in · $0.04 out · 33K context
- Voxtral SmallMistral AI · $0.1 in · $0.4 out · 33K context
- Command R7BCohere · $0.0375 in · $0.15 out · 128K context
- Llama 3.1 8BGroq · $0.05 in · $0.08 out · 131K context
- Nano BananaGoogle Gemini · $0.3 in · $30 out · 33K context