# Clairic vs Datalab (slim)

> Clairic scores 68.3 (B) to Datalab's 65.6 (B) for document extraction. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cloudflare-clairic-vs-datalab.md (~4,650 tokens) · this version ~2,530 tokens · JSON https://www.anchorterminal.com/compare/cloudflare-clairic-vs-datalab.json · canonical https://www.anchorterminal.com/compare/cloudflare-clairic-vs-datalab
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Clairic scores 68.3 (B) on agent readiness against Datalab's 65.6 (B), and leads in 3 of 7 scored categories. Datalab leads on maintenance & community. Both do document extraction.

- Clairic: B 68.3, rank #289 of 1486 · https://www.anchorterminal.com/tools/cloudflare-clairic.min.md
- Datalab: B 65.6, rank #413 of 1486 · https://www.anchorterminal.com/tools/datalab.min.md
- Clairic, good for Typed fields, estimates and next-step forecasts from emails, invoices, receipts and other text or images inside Cloudflare, each with a null probability and confidence. Ahead on Agent ergonomics, 78 against 73; Security & auth, 75 against 56; Transparency & trust, 81 against 68.
- Datalab, good for Hosted PDF and Office conversion and schema extraction with citations, from the team behind Marker. Ahead on Maintenance & community, 79 against 57.

| Category | Clairic | Datalab |
| --- | --- | --- |
| Reliability (16%) | 58 | 58 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 85 | 89 |
| Agent ergonomics (13%) | 78 | 73 |
| Security & auth (14%) | 75 | 56 |
| Payments & pricing (10%) | 40 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 57 | 79 |
| Transparency & trust (7%) | 81 | 68 |

| Fact (where they differ) | Clairic | Datalab |
| --- | --- | --- |
| Kind | Model API | HTTP API |
| Vendor | Cloudflare | Endless Labs, Inc. (Datalab) |
| Hosted endpoint | `https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clairic` | `https://www.datalab.to/api/v1` |
| Pricing | Freemium | Pay per use |
| Price for document extraction | not published | $15 per 1,000 pages |
| Licence | Proprietary hosted preview under Cloudflare's Self-Serve Subscription Agreement and the model page's own terms. Cloudflare says open weights will follow soon, with no date or licence named | Proprietary hosted service under Datalab's terms; the Marker and Surya code is open source and model weights are free under revenue and funding thresholds |
| Tools exposed | none | 0 |
| Last release | 2026-10-19 | 2026-11-06 |
| Terms last updated | 2025-09-12 | 2026-06-30 |
| Privacy policy last updated | no date given | 2026-06-30 |
| Terms or service can change without notice | yes | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Agent reviews | 3.3/5 (4) | none |

Why the edge:
- Maintenance & community, Datalab +22: Clairic 57 (Read for a model. Released on 19 October 2026, 13 days before this check, with no Clairic change in the Workers AI changelog since (30). For churn and notice, Cloudflare calls the endpoint an early checkpoint and says it will keep improving it with each checkpoint, under an unversioned ID, so the model can change under a caller with no stated notice (2 of 8). We found no stated minimum notice for Workers AI model changes, and the model page's terms let Cloudflare stop supplying Clairic. The changelog gave 22 days' notice for the 30 May 2026 retirements and none for the 28 July paid-only change (4 of 12). A dated changelog entry on launch day. Cloudflare's community and support channels weren't checked (9 of 15). Cloudflare's SDKs are current, TypeScript 7.3.0 and Python 5.9.0 tagged 2 October 2026, still the newest on 1 November per the Workers AI listing's check, with nothing specific to Clairic (10 of 15). No weights, code or package published to check. Cloudflare's Hugging Face account, read on 1 November, still holds only the three Clef models (2 of 10). 30 + 2 + 4 + 9 + 10 + 2 = 57.); Datalab 79 (Closed hosted service. Python SDK 0.9.1 on 6 November 2026 and a changelog entry on 4 November (30). Over twenty dated changelog entries since 8 August (20). Support by email, a Discord and public GitHub repositories for the open-source models; replies not sampled (12 of 15). An official Python SDK, current, no other languages (12 of 15). Package health not checked beyond release dates (5 of 10). 30+20+12+12+5 = 79.)
- Security & auth, Clairic +19: Clairic 75 (Read for a model API. Cloudflare API tokens limited to Workers AI permissions on one account, revocable, with optional expiry and IP address filtering, per the Workers AI listing's check of 9 October. Permission is per account, not per model (27 of 30). The Workers AI data usage page, updated 16 October 2026, says standard inference keeps no inputs or outputs after the response and Customer Content isn't used to train models. The Clairic post and model page add nothing on data (18 of 20, as Clef). Clairic reads untrusted text and images such as customer emails and receipts, and returns spans copied from them. The extraction models page says to match safeguards to risk and to check results or require human review before consequential or irreversible actions, and the post says handing a decision model typed values in place of a raw email narrows its injection exposure. No guidance on adversarial or injected input to Clairic itself was found (6 of 15). Per-request logs come through AI Gateway when it's used, and account audit logs record token changes, per the Cloudflare MCP listing's check (6 of 15). security.txt, re-read on 1 November, names a HackerOne programme and a disclosure policy, with no Expires field. Cloudflare's ISO certifications page, read on 1 November, says Cloudflare is certified to ISO 27001 (since 2019, now to its 2022 edition), ISO 27018 and ISO 27701, with a scope of the Cloudflare global cloud platform. 2 held back for the missing Expires field, as cloudflare-r2, cloudflare-workers-ai and cloudflare-ai-gateway read the same evidence (18 of 20, 15 before, when certifications went unread). 27 + 18 + 6 + 6 + 18 = 75.); Datalab 56 (Several hashed API keys with per-key 30-day spend caps, revoke-and-replace rotation, no scopes (24 of 30). Spend caps limit damage; results and files can be deleted by the key holder, and there's no read-only key (10 of 20). Returns document text with no prompt-injection guidance (2 of 15). cost_breakdown per request and usage tracking in the dashboard (8 of 15). A Secureframe trust centre and a SOC 2 report on the Team plan, TOTP enforcement for teams; no disclosure policy or security.txt found (12 of 20). 24+10+2+8+12 = 56.)
- Transparency & trust, Clairic +13: Clairic 81 (Closed for now. Cloudflare intends to release open weights soon, with no date or licence named, and no Clairic repository was public on Hugging Face on 1 November 2026. The terms are Cloudflare's Self-Serve Subscription Agreement plus the model page's own terms, which supply Clairic as is (15 of 30, closed with clear terms). The data usage page (16 October 2026) says no training and no retention for standard inference, and Cloudflare's privacy policy and DPA exist, per the Cloudflare MCP check (26 of 30). Dated notices on the Workers AI changelog but no deprecation policy, and the model terms say Cloudflare may stop supplying it with no refund or credit (10 of 20). Cloudflare's subprocessor page names third parties and group companies with locations, per the Cloudflare MCP check of 1 October. Where Clairic inference runs isn't stated (14 of 20). 15 + 26 + 10 + 14 = 65.); Datalab 68 (Closed service under terms effective 30 June 2026 naming Endless Labs, Inc. dba Datalab; the models and Marker are open source, with commercial weight use free only under revenue and funding thresholds (15 of 30). Results deleted about a day after processing, DELETE endpoints, and training on customer documents only on an opt-in that earns a discount; the privacy policy says public Playground submissions are used for training with no opt-out (22 of 30). A version policy that keeps inputs and outputs per API version and a migration guide for deprecated endpoints, with no notice period stated (14 of 20). EU processing offered at +25%; the sub-processor list sits in the trust centre, not read (10 of 20). 15+22+14+10 = 61.)
- Agent ergonomics, Clairic +5: Clairic 78 (Read as an API an agent calls for typed values, the way Clef is read for decisions. Answers are one typed value per field, so output stays small, and the 99 percentiles and the state text come back only on request. Fields that don't fit beside the state in one 8,192-token pass are split into parallel passes. The model page's example reports 3 passes and 655 input tokens for a 61-token state and 472 schema tokens, which matches the state being counted once a pass (61 x 3 + 472). No batch or caching found for Clairic (20 of 25). The caller fixes the output shape, with any number of fields, bounds and a grid for estimates and a 1 to 64 step horizon for forecasts (18 of 20). Workers AI errors carry internal codes and messages, and the response's `truncated` flag says when the state was cut. Nothing Clairic-specific, such as which field spec failed validation, is documented (14 of 20). Calls are stateless and safe to retry, with no retry guidance beyond the error table (15 of 20). Only `model` and `fields` are required, with defaults for `scale` and `null_threshold`. The body repeats the model the URL names, and there's no Clairic SDK. Cloudflare's TypeScript, Python and Go SDKs call the run endpoint for any model, per the Workers AI listing's check of 9 October (11 of 15). 20 + 18 + 14 + 15 + 11 = 78.); Datalab 73 (Output as Markdown, HTML, JSON or chunks, `page_range` to limit pages, and cost_breakdown on results (20 of 25). File listing and pipeline endpoints, little else to paginate (14 of 20). Typed errors with retry guidance an agent can follow (18 of 20). No idempotency key; the docs say to poll a known request ID instead of resubmitting, and webhooks may be retried (12 of 20). Official Python SDK and CLI, one language (9 of 15). 20+14+18+12+9 = 73.)