Claire Core: The Cybersecurity Expert Model API
Builders are hitting a wall with generic models. Claire Core by ClaireChains is a security-specific, expert-trained model API, purpose-built for internal security teams and cybersecurity startups assembling an agentic SOC. Run it locally or in the cloud.
Generic Models Weren't Built for the SOC
General-purpose LLMs are capable generalists, but security teams building agents quickly run into the same walls.
They don't speak security
Generic models reason about code and prose, not attack chains, detection logic, or adversary tradecraft. You end up burning context teaching the model your domain on every call.
Noise, not signal
Without security-specific training, general models over-trigger and hallucinate, flooding analysts with low-confidence output instead of decision-ready reasoning.
No control over deployment
Hosted-only APIs mean your sensitive telemetry leaves your environment, and you're locked out the moment a model is restricted or deprecated.
Built for Teams Automating the SOC
Ideal for internal security teams and cybersecurity startups building an agentic SOC. Drop Claire Core into the workflows where generic models fall short.
SIEM
Triage, correlate, and explain alerts with auditable reasoning your analysts can trust.
SOAR
Power autonomous playbooks and orchestration with a model that understands response actions.
SOC Workflows
Automate L1/L2 investigation, enrichment, and escalation across your existing tooling.
Pen Testing
Support red-team reasoning, recon, and exploit-path analysis with a security-native model.
Threat Intelligence
Summarise, correlate, and operationalise threat intel into detections and hunts.
Agentic SOC & More
Build multi-step security agents on a reasoning core trained for the domain - not retrofitted to it.
Run Locally or in the Cloud
Your data, your control. Deploy Claire Core wherever your compliance and latency requirements demand.
Local / On-Prem
Keep sensitive telemetry inside your perimeter for data sovereignty and air-gapped environments.
- Sensitive data never leaves your environment
- Runs in air-gapped and regulated networks
- Low-latency inference next to your data
Cloud API
Get started in minutes with a managed, scalable endpoint - no GPU procurement required.
- Production-ready API in minutes
- Scales elastically with your event volume
- Managed updates and uptime
The Power of the Core Model
Claire Core is built on a purpose-trained reasoning foundation derived from the open Datarus-R1 research lineage. Unlike models trained on isolated Q&A pairs, it learns from complete analytical trajectories - reasoning steps, tool execution, error traces, self-corrections, and conclusions - exactly the multi-step pattern that real SOC investigations require.
- ReAct-style agentic reasoning for multi-step security analysis
- 18-49% more token-efficient than comparable generic models
- Built on an open-weights, Apache-2.0 reasoning foundation (Datarus-R1, 14.8B params)
- Trained on full analytical trajectories, not isolated Q&A pairs
Foundation model details: Datarus-R1-14B on Hugging Face
Foundation Benchmarks
Reasoning benchmarks for the Datarus-R1 research foundation that Claire Core builds on.
Claire Core vs. General-Purpose Hosted Models
General-purpose models have shown what AI can do for security. Most are hosted-only and tuned for broad tasks. Claire Core is trained for the work a SOC actually does, and runs where you need it.
| Claire Core vs. General-Purpose Hosted Models | Claire Core | General-purpose hosted models |
|---|---|---|
| Availability | Available now to vetted security teams and cybersecurity professionals | Varies by provider |
| Training focus | Purpose-trained and optimised for cybersecurity SOC work | Broad general-purpose training, not security-specific |
| Primary use | SIEM, SOAR, SOC automation, pen testing, agentic SOC | General tasks, with security as one of many |
| Deployment | Local or cloud - your data, your control | Usually a hosted API only |
| Access model | Self-serve API for builders | Set by each provider |
Claire Core is available now to vetted security teams and cybersecurity professionals. It is trained and optimised for SOC work, not general tasks.
Request More Information
Tell us about what you're building. We'll follow up with API access details for your team.
FAQ
Frequently asked questions
What is Claire Core?
Claire Core by ClaireChains is a cybersecurity model available as an API. It is built for teams creating an agentic SOC: SIEM triage, SOAR playbooks, SOC workflows, threat intelligence and pen testing. It is available now to vetted security teams.
Can Claire Core run on-premise or air-gapped?
Yes. Claire Core runs locally, including in air-gapped and regulated networks, so sensitive telemetry never leaves your environment. It is also available as a managed cloud API if you prefer not to run GPUs yourself.
What model is Claire Core based on?
Claire Core builds on Datarus-R1, an open-weights reasoning model released under the Apache-2.0 licence with 14.8 billion parameters. Claire Core is trained further for security work, using full analytical trajectories rather than isolated question and answer pairs.
How is Claire Core different from a general-purpose model?
General-purpose models reason about code and prose. Claire Core is trained on attack chains, detection logic and investigation steps, so it needs less context per call and produces decision-ready reasoning instead of low-confidence output.
How do I get access to Claire Core?
Fill in the access request form on this page and tell us what you are building. We reply within one business day with API access details for your team.
Start Building on a Security-Native Model
Get API access to Claire Core and give your agents a reasoning core built for the SOC.
Request API access