Qwen3.5 OCR model for extracting text and structure from documents and images, currently China-region only.
Qwen3.5-OCR appears in Alibaba Cloud's China catalog without an equivalent globally available Model Studio endpoint. Cross-region deployment requires separate confirmation.
ActionDo not assume international availability; confirm region, data residency, and contract terms first.
Verify source| Company | Alibaba / Qwen |
|---|---|
| Release | 2026-06-16 |
| Release type | Model release |
| Parameters | Not disclosed |
| Architecture | Not disclosed |
| Context | 131,072 |
| Input modalities | text / image / file |
| Output modalities | text / structured_output |
| Tool use / function calling | Not disclosed |
| Structured output / reasoning | Confirmed: Structured output |
| Vision / audio / video | Confirmed: Vision |
| Open weights / License | No open weights / license not applicable alibaba-qwen-qwen3-5-ocr-current · License not applicable |
| Vendor API | Available Alibaba Cloud Model Studio China model catalogalibaba-qwen-qwen3-5-ocr-current · 2026-06-16 |
| OpenRouter | Not separately listed on OpenRouter |
| Pricing | Official pricing page |
| Benchmark | No reliable public source |
| Public signals | No reliable public source |
| Use cases | OCR / Document extraction / Layout understanding / document understanding |
| Claim evidence | Release / model specs / weightsAlibaba Cloud Model Studio China model catalogqwen3.5-ocr · 2026-06-16 |
| OpenRouter | Not separately listed on OpenRouter |
|---|---|
| OpenRouter listing | Not separately listed in the current OpenRouter public list |
| Mapped version | qwen3.5-ocr alibaba-qwen-qwen3-5-ocr-current |
| Pricing | Official pricing page |
| Context | 131072 |
| Speed/Latency | No reliable public source |
| Snapshot time | 2026-07-15T20:11:41.551Z |
| Source | View source |