# DeepSeek-OCR 2 vs HunyuanOCR 1.5 (slim)

> HunyuanOCR 1.5 scores 56.6 (C) to DeepSeek-OCR 2's 49.2 (D) for ocr. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-hunyuanocr.md (~3,600 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-hunyuanocr.json · canonical https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-hunyuanocr
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

HunyuanOCR 1.5 scores 56.6 (C) on agent readiness against DeepSeek-OCR 2's 49.2 (D), and leads in 2 of 4 scored categories. DeepSeek-OCR 2 leads on reach and risk. Both do ocr.

- DeepSeek-OCR 2: D 49.2, rank #147 of 160 open-weight models · https://www.anchorterminal.com/tools/deepseek-ocr-2.min.md
- HunyuanOCR 1.5: C 56.6, rank #114 of 160 open-weight models · https://www.anchorterminal.com/tools/hunyuanocr.min.md
- DeepSeek-OCR 2, good for Teams that want an Apache 2.0 OCR model on a small GPU and already run vLLM Ahead on Reach, 65 against 60; Risk, 50 against 45.
- HunyuanOCR 1.5, good for Teams outside the EU, the UK and South Korea that want one small model for OCR, extraction and image translation Ahead on Agent interface, 80 against 35; Documentation and upkeep, 48 against 22.

| Category | DeepSeek-OCR 2 | HunyuanOCR 1.5 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 60 |
| Risk (20%) | 50 | 45 |
| Agent interface (10%) | 35 | 80 |
| Documentation and upkeep (10%) | 22 | 48 |

| Fact (where they differ) | DeepSeek-OCR 2 | HunyuanOCR 1.5 |
| --- | --- | --- |
| Vendor | DeepSeek | Tencent (Hy team) |
| Licence | Apache-2.0 | Tencent Hunyuan Community License (not licensed in the EU, the UK or South Korea) |
| Last release | 2026-02-03 | 2026-08-28 |
| Terms last updated | no document linked | not read yet |

Why the edge:
- Agent interface, HunyuanOCR 1.5 +45: DeepSeek-OCR 2 35 (Chat template 10, no Jinja template in the repository and none in tokenizer_config.json.); HunyuanOCR 1.5 80 (Chat template 20, chat_template.jinja in the repository (930 characters).)
- Documentation and upkeep, HunyuanOCR 1.5 +26: DeepSeek-OCR 2 22 (Model card 2, Intended use is there, as the two prompts.); HunyuanOCR 1.5 48 (Model card 8, Intended use, the architecture by reference to 1.0's unchanged backbone, and the context (128K) are on the card.)
- Reach, DeepSeek-OCR 2 +5: DeepSeek-OCR 2 65 (Memory 30, the only build from DeepSeek is the BF16 safetensors file, 6.78 GB, and 6.78 GB × 1.2 = 8.1 GB, within 16 GB.); HunyuanOCR 1.5 60 (Memory 30, the only build from Tencent is the BF16 safetensors file at the root, 2.24 GB, and 2.24 GB × 1.2 = 2.7 GB, within 16 GB.)
- Risk, DeepSeek-OCR 2 +5: DeepSeek-OCR 2 50 (File safety 15, safetensors only, no .bin, .pt or .pth files (25), less 10 because the card's documented way to load it is trust_remote_code, which runs the rep…); HunyuanOCR 1.5 45 (File safety 25, safetensors only, no .bin, .pt or .pth files, and no Python at the root.)