# DeepSeek-OCR 2 vs Surya OCR 2.5 (slim)

> Surya OCR 2.5 scores 61 (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-surya-ocr-2-5.md (~3,650 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-surya-ocr-2-5.json · canonical https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-surya-ocr-2-5
- 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)

Surya OCR 2.5 scores 61 (C) on agent readiness against DeepSeek-OCR 2's 49.2 (D), and leads in 3 of 4 scored categories. DeepSeek-OCR 2 leads on 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
- Surya OCR 2.5: C 61, rank #82 of 160 open-weight models · https://www.anchorterminal.com/tools/surya-ocr-2-5.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 Risk, 50 against 45.
- Surya OCR 2.5, good for Small companies and researchers who need quick OCR with layout on a laptop or a small GPU and fit the licence Ahead on Reach, 90 against 65; Agent interface, 70 against 35; Documentation and upkeep, 57 against 22.

| Category | DeepSeek-OCR 2 | Surya OCR 2.5 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 90 |
| Risk (20%) | 50 | 45 |
| Agent interface (10%) | 35 | 70 |
| Documentation and upkeep (10%) | 22 | 57 |

| Fact (where they differ) | DeepSeek-OCR 2 | Surya OCR 2.5 |
| --- | --- | --- |
| Vendor | DeepSeek | Endless Labs, Inc. (Datalab) |
| Licence | Apache-2.0 | Modified OpenRAIL-M (free for research, personal use and companies under $5M in revenue and funding) |
| Last release | 2026-02-03 | 2026-10-29 |
| Terms last updated | no document linked | not read yet |

Why the edge:
- Agent interface, Surya OCR 2.5 +35: DeepSeek-OCR 2 35 (Chat template 10, no Jinja template in the repository and none in tokenizer_config.json.); Surya OCR 2.5 70 (Chat template 20, chat_template.jinja in the repository (2,872 characters).)
- Documentation and upkeep, Surya OCR 2.5 +35: DeepSeek-OCR 2 22 (Model card 2, Intended use is there, as the two prompts.); Surya OCR 2.5 57 (Model card 17, Intended use, limitations, the architecture (a Qwen 3.5-style vision-language model with separate detection models), parameters (689M), the servi…)
- Reach, Surya OCR 2.5 +25: 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.); Surya OCR 2.5 90 (Memory 30, Datalab's own Q8_0 GGUF is 0.63 GB with a 0.21 GB projector, and 0.84 GB × 1.2 = 1.0 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…); Surya OCR 2.5 45 (File safety 25, safetensors and GGUF only, no .bin, .pt or .pth files and no Python in the model repository.)