Qwen VL OCR
Qwen VL OCR is Alibaba's image to text model with a 38K context window and up to 8K output tokens, starting at $0.070 / 1M input and $0.160 / 1M output. A Qwen visual language model from Alibaba specialized for optical character recognition and document text extraction.
alibaba-qwen-vl-ocr |
| Image to Text |
| Active |
| Alibaba |
| 38K tokens |
| 8K tokens |
| Text |
| Text |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
Alibaba Qwen | $0.070 | $0.160 | $0.035 | $0.080 |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| EAGLE Qwen 2.5 3B Instruct | — | — | — | — | Available |
| Qwen3.6 Max Preview | 262K | $1.04 | $6.24 | Available | |
| Qwen3.6 27B | 262K | $0.320 | $3.20 | Available | |
| Qwen3.6 35B A3B | 262K | $0.150 | $1.00 | Available | |
| Qwen3.6 Plus | 1.0M | $0.325 | $1.95 | Available | |
| Qwen3 Max Thinking | 262K | $0.780 | $3.90 | Available | |
| Qwen3 Next 80B A3B | 128K | $0.140 | $1.20 | Available | |
| Qwen3 Max | 262K | $0.359 | $1.43 | Available | |
| Qwen3 Max Preview | 262K | $1.20 | $6.00 | Available | |
| Qwen3 Coder Plus | 1.0M | $0.650 | $3.25 | Available | |
| Qwen VL OCR | — | 38K | $0.070 | $0.160 | Current |