HunyuanOCR-1.5

Open weights Active Multimodal hunyuanocr-1-5

Upgrade of HunyuanOCR on the same ~1B backbone, adding speculative decoding and llama.cpp deployment.

Released
Jul 7, 2026
Context window
Not disclosed
Max output
Not disclosed
Parameters
1B
Input price
Not disclosed
Output price
Not disclosed

Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.

Pricing

No first-party API. This is an open-weights release you can run yourself.

Specifications

Developer
Tencent
Model type
Multimodal
Architecture
Not disclosed
Parameters
1B
Input
Text Image
Output
Text
Knowledge cutoff
Not disclosed
License
Custom open license
API access
No first-party API
Capabilities
Small LM Vision