# Chandra OCR 2 vs DeepSeek-OCR 2 (slim)

> Chandra OCR 2 scores 54.7 (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/chandra-ocr-2-vs-deepseek-ocr-2.md (~3,150 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/chandra-ocr-2-vs-deepseek-ocr-2.json · canonical https://www.anchorterminal.com/compare/chandra-ocr-2-vs-deepseek-ocr-2
- 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)

Chandra OCR 2 scores 54.7 (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 risk. Both do ocr.

- Chandra OCR 2: C 54.7, rank #127 of 160 open-weight models · https://www.anchorterminal.com/tools/chandra-ocr-2.min.md
- DeepSeek-OCR 2: D 49.2, rank #147 of 160 open-weight models · https://www.anchorterminal.com/tools/deepseek-ocr-2.min.md
- Chandra OCR 2, good for Small companies and researchers who need accurate document parsing on their own GPU and fit the licence Ahead on Agent interface, 70 against 35; Documentation and upkeep, 33 against 22.
- 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.

| Category | Chandra OCR 2 | DeepSeek-OCR 2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 65 |
| Risk (20%) | 45 | 50 |
| Agent interface (10%) | 70 | 35 |
| Documentation and upkeep (10%) | 33 | 22 |

| Fact (where they differ) | Chandra OCR 2 | DeepSeek-OCR 2 |
| --- | --- | --- |
| Vendor | Endless Labs, Inc. (Datalab) | DeepSeek |
| Licence | Modified OpenRAIL-M (free for research, personal use and companies under $2M in revenue and funding) | Apache-2.0 |
| Last release | 2026-06-26 | 2026-02-03 |
| Terms last updated | not read yet | no document linked |

Why the edge:
- Agent interface, Chandra OCR 2 +35: Chandra OCR 2 70 (Chat template 20, chat_template.jinja in the repository (7,622 characters), Qwen 3.5's template, with a copy in tokenizer_config.json.); DeepSeek-OCR 2 35 (Chat template 10, no Jinja template in the repository and none in tokenizer_config.json.)
- Documentation and upkeep, Chandra OCR 2 +11: Chandra OCR 2 33 (Model card 8, Intended use and the languages (over 90) are on the card.); DeepSeek-OCR 2 22 (Model card 2, Intended use is there, as the two prompts.)
- Risk, DeepSeek-OCR 2 +5: Chandra OCR 2 45 (File safety 25, one safetensors file, no .bin, .pt or .pth files and no Python in the model repository.); 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…)