Inference for faster, cheaper & smarter security agents
Balance alert volume and data control with one API for open and fine-tuned models, serverless and in your own cloud.
- NuNER Zero
- GLiNER relex Large
- Qwen3Guard 4B
- Your fine-tuned model
- GLM-5.3 Flash
- DeepSeek V4.1 Flash
- Gemma 4 31B
The leading security platforms already run on open models
-
crowdstrike.comSep 1, 2026
CrowdStrike Launches Frontier Models for Cybersecurity, Created with NVIDIA
SafeMind model training data comes from CrowdStrike Falcon sensor telemetry… CrowdStrike builds the models using NVIDIA Nemotron open models in collaboration with NVIDIA, its AI design partner.
-
blogs.cisco.comFeb 12, 2026
Accelerate Security Operations with Cisco’s New Security-Tuned Model
…the Splunk AI Assistant in Security summary skill is powered by a custom-tuned Foundation-Sec-8B-1.1-Instruct model… we are replacing previous Llama‑3.1‑70B model calls…
-
cloudflare.comAug 26, 2025
Block unsafe prompts targeting your LLM endpoints with Firewall for AI
Cloudflare has integrated Llama Guard directly into Firewall for AI… we chose Llama Guard 3, an open-source model based on the Llama architecture…
-
wiz.ioJun 10, 2025
Lean and Mean: How We Fine-Tuned a Small Language Model for Secret Detection in Code
We fine-tuned a small language model (Llama 3.2 1B) for detecting secrets in code… Customers are explicitly unwilling to share proprietary code with external LLM services…
Keep triaging when an attack floods your queue
Each job runs on a model sized for it, next to your app. When an attack floods your queue with alerts, you add GPUs to your own cluster instead of waiting on a provider’s quota.
Run a month of security analysis for 96% less
Task-sized open models do each job for a fraction of a frontier API’s price. Each line is priced from its task page, at an illustrative month’s volume.
- Tag actors, malware and tools in threat reports
$6,160$28 More names tagged right - Map how threats relate across reports
$8,854$47 More relations right - Screen prompts to your security copilot
$5,801$488 More harmful prompts caught - Classify alerts for triage
$2,393$350 Labelled correctly: SIE 87.5% · GPT-6 93.8%
Tuned on your task, an open model beats the frontier APIs at it
How each result was measured
- Possible fraud in bank messages
- BANKING77: 3,076 customer messages to a bank, 240 of them reporting a payment they don’t recognise or a card or phone lost, stolen or compromised, none among the 9,993 the model was tuned on. The share of those reports caught while 95% of the messages flagged are reports, each model’s threshold set on the scored messages; GPT-6 Luna at low effort.
- Contract-clause review
- LexGLUE UNFAIR-ToS: 3,882 Terms of Service clauses labelled by lawyers, none of them among the 5,532 the model was tuned on. F1 on the unfair class; each API at its best setting, with the lawyers’ annotation rulebook in its prompt.
- Business questions to chart specs
- Superlinked’s gd-1, August 2026: Gemma 4 31B tuned on generated questions, then scored once on a BI assistant’s 875-question benchmark, counting the answers that return the reference data. GPT-5.6 Sol at maximum reasoning was the strongest API. The training questions came from the benchmark’s own generator, which is the home advantage tuning on your own task gives.
Meet the vendor requirements of your government and enterprise customers
| What the rule asks | SIE Serverless | SIE in your cloud |
|---|---|---|
Use only FedRAMP-authorised cloud services US OMB M-24-15, Jul 2024“Agencies must obtain and maintain a FedRAMP authorization when the cloud product or service falls within the scope of this section.” | Not FedRAMP authorised For federal data, run SIE in your cloud | Runs in your authorised cloud Software installed in your own tenant |
Never train on government data US OMB M-25-22, Apr 2025Contracts must “permanently prohibit the use of non-public inputted agency data and outputted results to further train publicly or commercially available AI algorithms”. | Never learns from requests SIE serves fixed weights; a request never changes the model | Learns only what you train You fine-tune only on data you choose |
Assess each supplier’s security practices EU NIS2 Directive, Article 21Entities must “take into account the vulnerabilities specific to each direct supplier and service provider and the overall quality of products and cybersecurity practices of their suppliers and service providers”. | SOC2 Type 2 report For your customers’ supplier reviews | Code and weights to inspect Open source, on versions you pin |
Keep models and data portable US OMB M-25-22, Apr 2025“Protections against vendor lock-in can vary, but include requirements for vendor knowledge transfers, data and model portability”, among others. | Same API in your cloud The same models and calls move in-house | Free to self-host Apache 2.0 engine, runs without us |
Start on SIE Serverless, or run it under your control
SIE Serverless
We host the models; you call one API.
- No idle GPUs, pay for what you use
- Fits your stack: SDK, API, CLI, MCP
- Self-host the same open-source engine
- SOC 2 Type 2, US or EU data residency
- Create an account to try Serverless
SIE Cluster
Kubernetes in your own cloud, backed by our engineers.
- Terraform modules for your cloud
- Apache-2.0, same engine as Serverless
- GPU workers scale to zero between jobs
- Separate worker pools for each tenant
Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Google Cloud project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Azure subscription with the superlinked/sie/azure Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Alibaba Cloud account with the superlinked/sie/alicloud Terraform module. Docs: superlinked.com/docs/deployment. SIE Local
The open-source server on your own machine.
- Runs on your NVIDIA GPU
- One container, no cluster
- Process your data fully offline
- Same SDK and model IDs as Serverless
docker run --gpus all -p 8080:8080 ghcr.io/superlinked/sie-server:latest-cuda12-default Start from your task or your industry
Search and RAG
Documents
Text and LLM apps
- Chat Open LLM, OpenAI-style API
- Coding agents Tool calls for your coding agent
- Structured output Schema-valid JSON
- Classify text Your labels, no training
- Yes/no decisions Automate workflow checks
- Route requests Cheap or strong LLM, per request
- Extract names and dates People, orgs, places
- Knowledge graph Entities and their relations
- Translate text English into many languages