# Baidu Unlimited-OCR-2 vs ZAYA1-8B (slim)

> ZAYA1-8B scores 61 (C) to Baidu Unlimited-OCR-2's 54.2 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/unlimited-ocr-2-vs-zaya1-8b.md (~9,400 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/unlimited-ocr-2-vs-zaya1-8b.json · canonical https://www.anchorterminal.com/compare/unlimited-ocr-2-vs-zaya1-8b
- 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)

ZAYA1-8B scores 61 (C) on agent readiness against Baidu Unlimited-OCR-2's 54.2 (C), and leads in 2 of 4 scored categories. Baidu Unlimited-OCR-2 leads on agent interface. Both do open-weight models you run yourself.

- Baidu Unlimited-OCR-2: C 54.2, rank #133 of 160 open-weight models · https://www.anchorterminal.com/tools/unlimited-ocr-2.min.md
- ZAYA1-8B: C 61, rank #85 of 160 open-weight models · https://www.anchorterminal.com/tools/zaya1-8b.min.md
- Baidu Unlimited-OCR-2, good for Pipelines with an NVIDIA GPU that need long scanned or rendered documents parsed in one pass, with page order, cross-page tables and boxes kept Ahead on Agent interface, 75 against 60.
- ZAYA1-8B, good for People who want a small, fast reasoning model for maths and code and can live without tool calling Ahead on Reach, 80 against 55; Risk, 55 against 45.

| Category | Baidu Unlimited-OCR-2 | ZAYA1-8B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 55 | 80 |
| Risk (20%) | 45 | 55 |
| Agent interface (10%) | 75 | 60 |
| Documentation and upkeep (10%) | 50 | 50 |

| Fact (where they differ) | Baidu Unlimited-OCR-2 | ZAYA1-8B |
| --- | --- | --- |
| Vendor | Baidu | Zyphra |
| Licence | MIT (Hub metadata; the Hugging Face repository has no LICENSE file, and the GitHub code repository's LICENSE is the MIT text, copyright 2026 Baidu) | Apache-2.0 |
| Last release | 2026-10-26 | 2026-07-02 |

Why the edge:
- Reach, ZAYA1-8B +25: Baidu Unlimited-OCR-2 55 (Memory earns the full 30, since the only build is 6.69 GB of BF16 weights that need about 8 GB with the fifth added.); ZAYA1-8B 80 (Memory 30, the smallest build from Zyphra is the MXFP4-Experts repository, 5.85 GB, and 5.85 GB × 1.2 = 7.0 GB, within 16 GB.)
- Agent interface, Baidu Unlimited-OCR-2 +15: Baidu Unlimited-OCR-2 75 (Read for a document parser, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns.); ZAYA1-8B 60 (Chat template 20, chat_template.jinja in the repository (10,700 characters).)
- Risk, ZAYA1-8B +10: Baidu Unlimited-OCR-2 45 (File safety gets 15, safetensors only but loaded with trust_remote_code or through a prebuilt SGLang wheel from the repository.); ZAYA1-8B 55 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.)