deepopen
deepopen is an open-weight, non-autoregressive model for typed decisions, based on ModernBERT-large with 421 million parameters. It supports a 512-token context and is intended for English-language tasks.
What it does
Developers can use it to build local intent-classification and structured-decision workflows, such as routing requests or scoring urgency.
- Availability
- Install from the public GitHub repository
- Pricing model
- $0 self-hosted
- Deployment
- Can run on CPU or compatible GPU; supports local checkpoint directories
- Privacy
- Not established
- Licence
- Apache License 2.0; review separate model and dataset licenses
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- DeepOpen evaluates predefined questions over text or JSON and returns labels, scores, and probabilities. [1]
DeepOpen evaluates predefined questions over text or JSON and returns labels, scores, and probabilities.
GitHub new repositories. Quoted text is outside CC BY 4.0 and keeps its original rights. - The SDK provides choice, score, and noul decision types. [1]
The SDK provides `router_questions()`, `guard_questions()`, `moderation_questions()`, `triage_questions()`, and `email_questions()`.
GitHub new repositories. Quoted text is outside CC BY 4.0 and keeps its original rights. - Installation instructions install the package directly from the GitHub repository. [1]
Install from this repository; the installation instructions do not depend on a PyPI release named `deepopen`.
GitHub new repositories. Quoted text is outside CC BY 4.0 and keeps its original rights. - The quick start supports CPU use and compatible GPU environments. [1]
- Predictions can be wrong, and confidence scores are not a guarantee of correctness. [1]
Output types are constrained; predictions can still be wrong, and probabilities require validation on your own data.
GitHub new repositories. Quoted text is outside CC BY 4.0 and keeps its original rights. - Self-hosting avoids per-token API fees but still incurs hardware, electricity, and operating costs. [1]
Self-hosting avoids per-token API fees but still incurs hardware, electricity, and operating costs.
GitHub new repositories. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
GitHub new repositoriesOwner-controlled
https://github.com/deepopen-com/deepopen
Retrieved 2026-10-29 01:10 UTC
Verified
Versions
5| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 5 | 2026-10-24 00:44 UTC | material change | capability, access, pricing, availability, deployment | Current |
| 4 | 2026-10-23 00:24 UTC | material change | access, availability, pricing model, deployment | Current |
| 3 | 2026-10-21 12:53 UTC | evidence update | score | Current |
| 2 | 2026-09-25 13:08 UTC | material change | capability, access, availability | Current |
| 1 | 2026-09-24 13:41 UTC | publication | None | Current |
In briefs
1- New models and tools focus on typed decisions and long-context tasks Weekly brief 2026-W39
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.