ModelsParticula-JSON
Structured outputs,every time.
Particula-JSON turns documents and free text into schema-valid JSON. Constrained decoding means the schema you provide is the schema you get back, on every request. One small model on a single GPU inside your network: no vendor cloud, no per-token meter.
YOUR-GPU · PARTICULA-JSON
$ POST /v1/extract · invoice_2041.pdf
→ particula-json · schema locked
→ "invoice_id": "INV-2041"
→ "total": 12480.00 · "currency": "USD"
✓ 200 · 41 ms · valid JSON
ready
PARTICULA-JSON · YOUR HARDWARE · ZERO TELEMETRY
What it doesSee it on your data
Schema in, schema outDecoding is constrained against the JSON Schema you send with the request. Malformed or extra-field output is structurally impossible, so parsers downstream never break.
Documents and free textInvoices, emails, forms, and logs. A bundled pre-processor handles PDF layout and OCR text before the model sees it.
99.8% schema passField-level accuracy on our held-out extraction suites. Our own measurement: the shipped harness reproduces it on your documents.
Fails loudly, never guessesFields the model cannot ground in the source come back null with a reason code, so silent fabrication does not reach your database.
Spec sheetCompare all six
Context window32K tokensRoughly 60 pages of dense document text per request.
Median latency41 ms medianBatch 1 on the reference single-GPU deployment. Our own measurement: the shipped harness reproduces it on your hardware.
InterfaceOpenAI-compatible RESTServed by vLLM, deployed with Docker Compose or Helm. Drop-in for existing OpenAI client code.
Hardware1× 24 GB GPUL4 or A10 class. Sizing reviewed before the pilot.
Fine-tuningLoRA on your dataTuning jobs are included with Enterprise. A few hundred labeled examples from your pipeline is usually enough to move the needle.
How deployment worksStart at step 01
01Discovery call
30 minutes, no slides. Your task, your data shape, and the security constraints around it. If this model is the wrong fit, we say so on the call.02Pilot install
Containerized deployment to staging in your VPC or on-prem, on the same stack as Lumen and Notetaker. The eval harness runs on your data and the numbers go into the pilot agreement.03Production rollout
Runbook handoff, operator training, and 90 days on call. After that it is yours to operate, no vendor dependency.More modelsAll six models
Request a demo
“Bring a hundred real examples from your pipeline. We run the model on them live, the harness scores the output in front of you, and you decide with numbers instead of a sales deck.”
Sebastian Mondragon, Founder of Particula Tech
Request a demo30 minutes · no sales deck