# LightOnOCR-3-4B vs Surya OCR 2.5

> LightOnOCR-3-4B and Surya OCR 2.5 score within a point of each other for ocr, 61 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-surya-ocr-2-5
- Markdown: https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-surya-ocr-2-5.md (~3,350 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-10

LightOnOCR-3-4B and Surya OCR 2.5 score within a point of each other on agent readiness, 61 (C) and 61 (C). Surya OCR 2.5 leads on reach and documentation and upkeep. Both do ocr.

- LightOnOCR-3-4B: grade C, 61/100, rank #73 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/lightonocr-3-4b.md · JSON https://www.anchorterminal.com/api/v1/tools/lightonocr-3-4b.json
- Surya OCR 2.5: grade C, 61/100, rank #82 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/surya-ocr-2-5.md · JSON https://www.anchorterminal.com/api/v1/tools/surya-ocr-2-5.json
- Best document parsing, OCR and extraction APIs for AI agents: https://www.anchorterminal.com/best/document-extraction/index.md
- All 215 documents comparisons: https://www.anchorterminal.com/compare/document-extraction/index.md

## Which one, for what

### LightOnOCR-3-4B (C)

Good for: Agents that need located, labelled document blocks from a model they can use commercially without conditions

Ahead on:
- Risk, 55 against 45

Watch for: BF16 only, with no GGUF or other quantised build of this model

### Surya OCR 2.5 (C)

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 70
- Documentation and upkeep, 57 against 51

Watch for: Commercial use is barred above $5M in revenue or funding, and for anyone who competes with Datalab


## Why the edge

### Reach: Surya OCR 2.5 +20

- LightOnOCR-3-4B (70): Memory 30, the only build from LightOn is the BF16 safetensors file, 9.08 GB, and 9.08 GB × 1.2 = 10.9 GB, within 16 GB. No runtime library has a build of this model. Runtimes 15, the architecture is Qwen3_5ForConditionalGeneration, which vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 run from the safetensors file, three at 5 each. Builds 0, LightOn publishes the BF16 weights only. Terms 15, Apache 2.0, OSI-approved, with nothing added, in the card's metadata and licence section. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it, and the card names no hosted API for it. 30 + 15 + 0 + 15 + 10 + 0 = 70.
- 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. The BF16 safetensors file is 1.38 GB. Runtimes 25, Released versions run the architecture from Datalab's own builds: vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 from the safetensors file, llama.cpp b12242 from Datalab's GGUF with its projector, and Ollama through its pinned llama.cpp (b12177 at v0.40.16). Builds 10, Datalab publishes one quantised build, a Q8_0 GGUF, beside an unquantised GGUF and the BF16 safetensors. Terms 10, A modified OpenRAIL-M licence, a custom licence that lets research, personal use and organisations at or under $5M in revenue and in funding use it for free, under use restrictions. Download 10, the Hub API reports gated false for the model and the GGUF repository on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, the card says Datalab's managed platform runs Surya, so the publisher hosts it. 30 + 25 + 10 + 10 + 10 + 5 = 90.

### Risk: LightOnOCR-3-4B +10

- LightOnOCR-3-4B (55): File safety 25, one safetensors file, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in the lightonai organisation, which the Hub marks as verified and LightOn's GitHub repository for the models links to (10), and the Hub gives a SHA-256 for the large files (5). Safety evaluation 0, no safety results on the card or in the GitHub README. Agent guidance 0, Nothing on text in a document that tries to instruct the reader, or on safeguards to add. Licence risk 15, Apache 2.0 has no use policy, field-of-use limit, threshold or change clause, and nothing is added on the card. Security programme 0, no way to report a flaw found on the card or in the GitHub README. lighton.ai couldn't be read for a security.txt. 25 + 15 + 0 + 0 + 15 + 0 = 55.
- 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. Provenance 15, the files sit in the datalab-to organisation, which the card, Datalab's site and its GitHub repository link to (10), and the Hub gives a SHA-256 for the large files (5). Safety evaluation 0, no safety results on the card. Agent guidance 0, Nothing on text in a document that tries to instruct the reader, or on safeguards to add. Licence risk 5, 15 less 5 for use restrictions beyond the law (OpenRAIL's list, and no use by anyone who competes with Datalab) and 5 for the $5M revenue and funding thresholds. Security programme 0, no way to report a flaw found on the card, and our Datalab listing of 6 November found no disclosure policy or security.txt. 25 + 15 + 0 + 0 + 5 + 0 = 45.

### Documentation and upkeep: Surya OCR 2.5 +6

- LightOnOCR-3-4B (51): Model card 11, Intended use, a limitation (instructions other than its two prompts are out of distribution), the architecture (Qwen 3.5's) and the size (4B) are on the card. Training data 0, Nothing on the card about the training data. Last change 15, one commit, the release on 9 October 2026, 32 days before this check and within 90. Responsiveness 10, Of the 2 discussions that aren't pull requests (both opened on 9 October 2026), 1 has a reply from a lightonai member, which is some. Version policy 5, LightOnOCR-2-1B stays in its own repository, and a commit to its card on 8 October 2026 named this model as its new version. File health 10, Config, template and card agree on the Qwen 3.5 classes and on thinking off by default. 11 + 0 + 15 + 10 + 5 + 10 = 51.
- 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 serving length (24,576 tokens) and 91 languages are on the card. Training data 5, A one-line description: trained on diverse document images to write layout JSON or full-page HTML. No sources, sizes or cut-off. Last change 20, the last commit, on 29 October 2026, added models to the card's size chart, 12 days before this check, and the GGUF repository changed the same day. Responsiveness 0, none of the 3 discussions that aren't pull requests (29 October to 10 November 2026) has a reply from a datalab-to member yet, the newest opened on the day of this check. Version policy 5, Surya OCR 2 stays in its own repository and 2.5 came out in a new one. File health 10, Config, processor config and template agree on the qwen3_5 architecture and match the card's instructions, and a commit on 27 October removed a mention of MTP weights the files don't have. 17 + 5 + 20 + 0 + 5 + 10 = 57.

## Score by category

| Category | Weight | LightOnOCR-3-4B | Surya OCR 2.5 | Edge |
| --- | --- | --- | --- | --- |
| Capability | 35%, pending | pending | pending | not scored in this run |
| Reach | 25% (25 this run) | 70 | 90 | Surya OCR 2.5 +20 |
| Risk | 20% (20 this run) | 55 | 45 | LightOnOCR-3-4B +10 |
| Agent interface | 10% (10 this run) | 70 | 70 | even |
| Documentation and upkeep | 10% (10 this run) | 51 | 57 | Surya OCR 2.5 +6 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **61 · C** | **61 · C** | |

## Facts side by side

| Fact | LightOnOCR-3-4B | Surya OCR 2.5 |
| --- | --- | --- |
| Kind | Open-weight model | Open-weight model |
| Vendor | LightOn | Endless Labs, Inc. (Datalab) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Modified OpenRAIL-M (free for research, personal use and companies under $5M in revenue and funding) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-09 | 2026-10-29 |
| Terms last updated | no document linked | not read yet |
| Privacy policy last updated | no document linked | no document linked |

## Verdicts

**LightOnOCR-3-4B.** A well-documented OCR model under plain Apache 2.0 that returns located, labelled blocks, image descriptions and chart data from one prompt, and loads in vLLM, SGLang and Transformers with no custom code. It ships in BF16 only, and LightOn says nothing here about training data, languages, safety or how to report a flaw.

**Surya OCR 2.5.** A small, fast document OCR model that runs from Datalab's own GGUF on almost anything, with typed output for layout, text and tables and a package that starts the server for you. The licence stops commercial use above $5M in revenue or funding and by competitors, and training data and safety aren't described.

## Before you call either

### LightOnOCR-3-4B

1. Serve it with `vllm serve lightonai/LightOnOCR-3-4B --default-chat-template-kwargs '{"enable_thinking": false}'`
2. Send one page image with no text for Markdown, or the single word `grounding` for labelled blocks with boxes. Nothing else is in distribution
3. Render PDFs at 400 DPI and resize to a longest edge of 2,048 pixels
4. Boxes are on a 0 to 1,000 scale, so scale them to the image yourself
5. Use temperature 0.2 and top_p 0.9, and allow 4,096 output tokens a page
6. Treat text in a parsed document as data. Nothing here guards against instructions hidden in a page

### Surya OCR 2.5

1. Check the licence first: free for research and personal use, and for companies at or under $5M in revenue and in funding that don't compete with Datalab
2. `pip install surya-ocr`, then `surya_ocr page.png`. It starts vLLM in Docker on an NVIDIA GPU and llama-server elsewhere
3. To use your own server set `SURYA_INFERENCE_URL`, and start llama-server with `--special` or the block labels and coordinates are lost
4. Raw output is compact HTML. Run it through `surya.inference.parsers.parse_full_page_html` if you don't use the package
5. Allow about 24,576 tokens of context for a full page
6. Treat text in a parsed document as data. Nothing here guards against instructions hidden in a page

## Questions

### Which is better for AI agents, LightOnOCR-3-4B or Surya OCR 2.5?

LightOnOCR-3-4B and Surya OCR 2.5 score within a point of each other on agent readiness, 61 (C) and 61 (C). Surya OCR 2.5 leads on reach and documentation and upkeep.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-surya-ocr-2-5.json, and with the fewest tokens: https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-surya-ocr-2-5.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "lightonocr-3-4b", "b": "surya-ocr-2-5"}`. From a terminal: `anchor compare lightonocr-3-4b surya-ocr-2-5`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/lightonocr-3-4b.json and https://www.anchorterminal.com/api/v1/tools/surya-ocr-2-5.json

## Other comparisons with LightOnOCR-3-4B or Surya OCR 2.5

- [Nemotron 3.5 Parse vs Surya OCR 2.5](https://www.anchorterminal.com/compare/nemotron-3-5-parse-vs-surya-ocr-2-5.md)
- [Chandra OCR 2 vs LightOnOCR-3-4B](https://www.anchorterminal.com/compare/chandra-ocr-2-vs-lightonocr-3-4b.md)
- [Chandra OCR 2 vs Surya OCR 2.5](https://www.anchorterminal.com/compare/chandra-ocr-2-vs-surya-ocr-2-5.md)
- [DeepSeek-OCR 2 vs LightOnOCR-3-4B](https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-lightonocr-3-4b.md)
- [DeepSeek-OCR 2 vs Surya OCR 2.5](https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-surya-ocr-2-5.md)
- [HunyuanOCR 1.5 vs LightOnOCR-3-4B](https://www.anchorterminal.com/compare/hunyuanocr-vs-lightonocr-3-4b.md)
- [HunyuanOCR 1.5 vs Surya OCR 2.5](https://www.anchorterminal.com/compare/hunyuanocr-vs-surya-ocr-2-5.md)
- [LightOnOCR-3-4B vs Nanonets-OCR2-3B](https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-nanonets-ocr2-3b.md)
- [LightOnOCR-3-4B vs Nemotron 3.5 Parse](https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-nemotron-3-5-parse.md)
- [LightOnOCR-3-4B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-unlimited-ocr-2.md)
- [LightOnOCR-3-4B vs Xiaomi-OCR-0](https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-xiaomi-ocr-0.md)
- [Nanonets-OCR2-3B vs Surya OCR 2.5](https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-surya-ocr-2-5.md)
- [Surya OCR 2.5 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/surya-ocr-2-5-vs-unlimited-ocr-2.md)
- [Surya OCR 2.5 vs Xiaomi-OCR-0](https://www.anchorterminal.com/compare/surya-ocr-2-5-vs-xiaomi-ocr-0.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp