The backbone of your AI integration.
Every team integrating AI rebuilds the same stack: provider gateway, prompt versioning, evals, cost dashboards. 2kw.ai is that stack — production-ready, on open standards (OpenAI-compatible API, OpenTelemetry tracing). Your team builds the product, not the plumbing.
From documents to data.
Extract structured data from documents, 2D drawings, and 3D CAD files. Define your schema once — we handle the rest.
The boring parts, already solved.
Real teams. Real workloads. Skip the plumbing.
Hekitec
Hundreds of supplier documents and inquiries weekly. 2kw.ai extracts part numbers, quantities, specs — straight into procurement. Hours of manual work, now in the background.
MKD IoT Platform
Our own IoT platform runs on 2kw.ai's gateway. Operators ask questions in plain language — gateway routes to the right model, tracks the cost, returns an answer in seconds.
Simple, transparent pricing.
Choose the plan that fits your workload. Scale up as you grow. No hidden fees, no surprises.
For small teams getting started.
- ✓2 seats included
- ✓Extra seats €25 / month each
- ✓1x usage
- ✓1 surface installation
- ✓2 parallel agent runs
- ✓30-day trace retention
- ✓Opt-in extra usage, capped by you
- ✓Standard support
For teams that build agents every day.
- ✓5 seats included
- ✓Extra seats €25 / month each
- ✓5x usage
- ✓3 surface installations
- ✓5 parallel agent runs
- ✓90-day trace retention
- ✓Opt-in extra usage, capped by you
- ✓Bring your own keys (BYOK)
- ✓Standard support
For organisations running AI in production.
- ✓10 seats included
- ✓Extra seats €25 / month each
- ✓10x usage
- ✓10 surface installations
- ✓10 parallel agent runs
- ✓180-day trace retention
- ✓Opt-in extra usage, capped by you
- ✓Bring your own keys (BYOK)
- ✓Priority support and audit
Usually from €1,500 a month, negotiated.
- ✓Everything in Business
- ✓Seats and usage by contract
- ✓Parallel runs and capacity by contract
- ✓Trace retention by contract
- ✓SLA
- ✓Dedicated infrastructure or on-premise option
What 1x, 5x and 10x cover: see worked examples
Frequently asked questions.
Need something not covered here? Talk to us.
What formats does 2kw.ai support?
26 supported formats: 17 document and image input formats plus 9 audio formats for transcription. The 17 are PDF, DOCX, XLSX, PPTX, CSV, MSG, EML, HTML, Markdown, TXT, AsciiDoc, ZIP, images (any image/* type), and the engineering formats DXF, DWG, STEP and GEO (TRUMPF). Documents convert to Markdown, plain text, JSON, or HTML. Audio transcription covers FLAC, MP3, MP4, MPEG, MPGA, M4A, OGG, WAV, and WebM — with output as text, JSON, SRT, or VTT subtitles. Large files split automatically, results merged into clean structured output.
How does the multi-provider gateway work?
One OpenAI-compatible endpoint that routes requests to any major AI provider — OpenAI, Azure OpenAI, Anthropic, xAI, Mistral, or self-hosted models via Ollama. Switch providers by changing a config line, not your codebase. Built-in cost tracking and budget alerts keep spending transparent.
Can I bring my own API keys (BYOK)?
Yes — on Team, Business and Enterprise. Connect your existing OpenAI, Azure OpenAI, Anthropic, xAI, or Mistral credentials, or your own Ollama server, and route through the platform. Keys are encrypted at rest. A BYOK request's model charge does not count against your plan's usage. Note: data residency and GDPR guarantees apply to 2kw.ai's built-in models. With BYOK, your data flows to the provider you chose under their terms.
Is there a CLI and AI-assistant integration?
Yes. All features are accessible via an MCP server that integrates 2kw.ai directly into Claude Code, Cursor, or Windsurf — your agent can update a schema, test it, and trigger extractions without leaving the editor. There's also a CLI to use 2kw.ai features and integrate them into agentic workloads.
Can I use 2kw.ai with my existing systems?
Yes. Standard REST API integrates with anything. The OpenAI-compatible interface means existing OpenAI integrations work out of the box — just change the base URL.
How does 2kw.ai ensure extraction quality?
Every extraction follows a schema you define — field names, data types, structure. Schemas are version-controlled so you can iterate without breaking production. For large documents, automatic chunking splits the input and merges results back against your schema. Async processing handles heavy workloads with retries. If something doesn't match your schema, you see it immediately.
Is there a free trial or demo?
Yes. Starter comes with a 7-day free trial — no charge until the trial ends, cancel anytime. Prefer a guided walkthrough? We also offer a no-commitment 15-minute demo where we run extraction on your own documents so you see real results before deciding.
Stop building AI infra from scratch.
Multi-provider gateway, document extraction, cost control, and evals with regression testing — out of the box. So your team can focus on what AI actually does for your business.