Usage, cost, and corrections
in a single view
See where model spend goes, what reaches users, and how often Gateway fixes invalid output before users see it.
7% of UI generations fail silently in production
Failures are easy to miss because the request still succeeds. Based on 1,285 production failures observed over 15 days.
- 44%No valid root
- 36%Reference graph
- 16%Enum, type and
argument errors - 4%Truncation
OpenUI produces more structurally valid output than Google A2UI and Vercel json-render, with about half the tokens and streaming time. Gateway catches what remains.
Fix invalid output before users see it
Every response is validated against your component library. Invalid ones are repaired in the streaming path. Over 99% render successfully.
Provider pricing
Tokens are billed at provider rates, with no Gateway markup.
SDK support
Chat Completions and Responses endpoints work with your existing SDKs.
Bring your own keys
Use your existing OpenAI, Anthropic, or Google Vertex credentials and commitments.
Works with other gateways
Run Gateway behind any OpenAI-compatible gateway, including Portkey.
Keep your cache
Add Gateway without changing your upstream cache configuration.
Broad model support
Use any model through one OpenAI-compatible API. View routing.
Keep your existing model provider,
Add reliability with Autofix.
Keep your existing model calls, direct or through AI gateways. Add one Autofix API call to repair invalid generations before users see them.
View docsAdopt it by changing
your base URL
- 1Generate an API key
Create a Gateway key in the OpenUI console.
- 2Update your base URL and model
Use the Gateway endpoint as your base URL and choose any provider/model identifier.
- 3Enable Gateway in your prompt
Include your component schema so Gateway can validate each response.
const client = new OpenAI({ apiKey: process.env.THESYS_API_KEY, baseURL: "https://api.thesys.dev/v1/embed",});
const response = await client.chat.completions.create({ model: "openai/gpt-5", messages: [ { role: "system", content: generatePrompt({ cloud: true }) }, ...messages, ],});Built for enterprise requirements
View trust centreZero data retention
Chat Completions requests use zero data retention by default.
Your data stays yours
Your Gateway data stays private and is never used to train models.
Compliance
Find GDPR, SOC 2, and ISO 27001 evidence in the Trust centre.
Provider fallbacks
Gateway switches providers if one fails, keeping the same model.
Live service status
View current and historical uptime on our service status page.
Private deployment
Deploy in your VPC or self-host in your own environment.
Built to scale
with your usage
Plans start free. Each response uses one API call plus LLM tokens at provider rates, with corrections included.
Gateway plans. Annual billing selected; prices shown per month.
Free
$0- Includes
- 3K API calls/month
- Bring your own LLM key
- Style customizations and popular LLM support
- Discord community support
Build
$49/mo$588 annually- Everything in Free
- 25K API calls/month
- $0.002 per additional call
- Higher request priority and rate limits
- Email support
Grow
$499/mo$5,988 annually- Everything in Build
- 500K API calls/month
- $0.001 per additional call
- Highest request priority and rate limits
- Priority support and solutions engineering
- SSO/SAML
Scale
Custom- Everything in Grow
- Run in your VPC or self-host
- Custom rate limits and usage controls
- Compliance, SLAs, and support guarantees
Frequently asked questions
Have another question? Join our Discord.
Do I need OpenUI Gateway to use OpenUI?
No. OpenUI works without Gateway. You can call any supported LLM directly and use generatePrompt to create the system prompt.
For production applications, OpenUI Gateway adds validation and automatic corrections for generated UI, model routing, and provider fallbacks through an OpenAI-compatible API.
What happens to my data?
Your Gateway data is never used to train models. Chat Completions requests use zero data retention by default.
Can I use my existing OpenAI or Anthropic credits?
Yes. Bring your own key (BYOK) to use your existing OpenAI or Anthropic credits and commitments. BYOK carries no platform fee.
I already use open-source OpenUI. How do I add Gateway?
Create a Gateway API key, update your base URL and model, and enable Gateway in your prompt. The integration guide covers the full setup.
You can also give the setup prompt to your coding agent or book a call for help.
Can I use OpenUI Gateway with Portkey or another gateway?
Yes. Run OpenUI Gateway behind any OpenAI-compatible gateway, including Portkey.
Will my cache configuration work?
Yes. OpenUI Gateway honors your upstream cache configuration.
Which model handles corrections, and are they billed separately?
Corrections use a dedicated model tuned for low latency, which we continue to improve. All correction calls are included in your plan and are not billed separately.
Do I need OpenUI Observability with Gateway?
No. OpenUI Gateway and OpenUI Observability work independently. Gateway does not require Observability.
We recommend using both. Gateway makes generated UI more reliable. Observability shows what users experienced and whether it worked.