Questions, answered plainly.

The control plane between your application and the AI providers you already pay. You connect your own provider accounts; one API covers text, image, video and audio across them; and INFRO handles routing, retries, failover, request logs, cost attribution and policy. You keep the models and the accounts you already chose — what changes is that there is one integration, and one place the cost and latency of every request is visible. Your providers still bill you for model usage, at your rates; INFRO charges a subscription for the software.

Yes. The gateway is deployed at api.infro.io and the console at dash.infro.io, and accounts are self-serve: create one, choose a plan and start the trial at checkout. Every capability we describe carries the release it lands in rather than being implied to exist.

If you use one model from one vendor and nobody has asked what it costs, you probably should go direct — that is a real answer and we would rather give it than waste your evaluation. INFRO earns its place when at least one of these is true: you run several models across several vendors, a provider incident has taken your product down, someone has started asking which customer or feature is spending what, or provider keys have started appearing in more than one place. You still call the same providers on the same accounts; you stop owning the integration, the failover and the accounting between them.

Create an account at dash.infro.io and verify your email address. You create your organization, choose a plan and add a card at checkout, and your 14-day trial starts when that checkout completes. At the end of day 14 the plan you have selected is charged automatically — cancel before day 14 and you won't be charged. Your providers keep billing you directly for model usage throughout.

Nothing. 0% markup on model spend, and it is structural rather than a promise: your requests run on your own provider accounts under your own credentials, so your provider invoices you directly and INFRO is never party to that transaction. There is no arrangement under which we could take a percentage of it. What INFRO charges is a flat subscription for the control plane — the gateway, request logs, cost attribution, budgets, policy and the audit log — and it is priced on gateway requests and organization features, never on tokens.

No. A model id resolves to the model that id names — no smaller variant, no quantized build, no shortened context — and your request reaches your provider as you wrote it. If a model id ever resolves to something else, that is a bug and a serious one. What INFRO adds is around the request rather than inside it: which of your connections served it, what it is estimated to cost you, whether a fallback rescued it, and whether it was allowed by your policy.

Far less than a migration, and it can start with one application. For text the endpoint speaks the OpenAI request and response shape, so a team changes the base URL, the key, and the model string, and keeps its client library, request bodies and response parsing. INFRO adds fields such as the provider and estimated cost to the response, and it can refuse a request for reasons a provider would not — a budget, a model policy, no connected provider — so those error codes are worth handling. Image, video, and audio use one consistent INFRO shape across every model, which is new code, but it is new code a team would otherwise have written per vendor. Nothing requires a company-wide cutover: teams adopt one application at a time, and the organization gets routing, budgets, and policy over each one as it arrives.

Yes. INFRO serves TypeSafe's POST /v1/systemone with TypeSafe's request body and model names, so TypeSafe's SDK works against INFRO with a new base URL and an INFRO gateway key. Each decision runs on your own TypeSafe account and TypeSafe bills you for it directly. Before TypeSafe is called, INFRO checks the key and any spend limit; afterwards it returns TypeSafe's answers with the version that answered and an estimated cost, and records the request.

Through one organization with projects and environments under it. Invite members with roles (owner, admin, developer, analyst), give each member and project its own spend ceiling, restrict which models each project may call, and read the audit log for who changed what. Each team gets its own keys, budget and model policy, so a runaway workload in one project cannot spend another team's allowance — while the organization keeps a single view across all of them. From the Business plan, people sign in through your own identity provider over SAML or OIDC, and your directory can create and deactivate their INFRO membership over SCIM.

It adds a hop, and pretending otherwise would insult you. Requests enter Cloudflare’s network at the location nearest your caller, and the gateway itself runs in Frankfurt, next to its database — so a caller far from Europe adds the network distance to Frankfurt before the provider call starts. The routing-overhead target of under 40 milliseconds is a target, stated as one, measured from Frankfurt, because there is no production traffic yet to measure. Two things keep the hop honest: every request records its total time beside the provider’s own time in the console, so the number that matters gets measured on your workload rather than asserted by us, and long renders are dominated by generation time, where milliseconds of routing are noise.

That is the design. You connect the provider accounts you already hold, so your negotiated rates, committed spend, discounts, quotas and enterprise agreements keep applying exactly as they do today — your provider bills you, at your prices, and INFRO takes none of it. If you have negotiated rates below the published ones, the Team plan and above let you enter them in the console, and every cost figure INFRO shows you is then computed from yours rather than from a list price. Leaving is the same two lines as arriving: change the base URL and the key back, and your provider accounts are untouched because they were always yours.

Routes are scored against live error rate, latency, and rate-limit pressure, so a degrading route leaves rotation. On a timeout or a 5xx before the response has started streaming, the request is retried on another route. Your application sees a successful response instead of somebody else's incident. Once a stream has started we cannot silently restart it — a partial response is surfaced as one rather than quietly re-rolled.

We become one more dependency — that is the honest cost of the trade, and you should price it in. Three things make it survivable. The status page runs on a separate, far simpler deployment than the gateway and checks the gateway from your own browser. Text speaks the OpenAI shape, so keeping a direct provider key and a base-URL switch in your config is a two-line contingency we actively recommend. And there is no published uptime SLA, because a service with no operating history cannot honestly offer one; an enterprise agreement can carry a contractual one.

Yes, and the migration back is the same two lines that brought you in. Retrieve request and usage history through the public APIs, or download it as CSV from the request log and Analytics, and keep it in your own systems before it leaves your plan's queryable history window. There are no scheduled or emailed exports.

We never train on your prompts, inputs, or outputs, and we never sell them. Usage metadata supports platform metering, cost estimates and governance. Optional prompt and response logging is off by default and limited by your plan. Job records and generated media needed for delivery are separate. Your AI providers' data-use and retention settings remain governed by your agreements with them.

Not yet, and we will not claim otherwise. Regional processing requires infrastructure entitlements we have not purchased, and a hostname that merely looks European is a compliance claim a customer can falsify in one request. When it is genuinely enforced we will say so; until then, assume requests are processed wherever capacity is, and treat that as a reason to talk to us before signing anything that depends on residency.

Yes, in the console. The Playground runs text, image, video, speech and transcription on one of your own connections or through a gateway key, and Copy cURL gives you the same request as an API call. Its history is kept in your browser, not by INFRO; the call itself is recorded like any other request and billed by your provider.

Two separate bills that never move together. Your providers invoice you for model usage, directly, at your own rates — INFRO is not in that transaction and takes 0% of it. INFRO invoices you for a plan: a flat monthly or annual subscription for the control plane, priced on gateway requests, seats, projects and organization features rather than on tokens. Four plans, from $35 a month, each with a 14-day trial that takes a card at checkout and converts automatically unless you cancel before it ends; annual is charged once for the year and saves about two months of the monthly price. Committed volume gets an enterprise agreement with invoicing. Provider spend never appears on an INFRO invoice.

The models your own provider accounts serve. INFRO does not supply models: you connect your OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock, xAI, Mistral, Groq or other accounts, or any server that speaks the OpenAI API, and your applications call those providers' models through INFRO on your credentials. A new model your provider releases is callable by its id as soon as your account can reach it, with a mapping on the connection where the provider needs one. The providers you can connect are listed on /providers, with a reference catalog of 299 models used to estimate what each request costs on your provider's bill.

As an async job. You submit, get a job id back immediately, then either poll the job endpoint or — better — receive a signed webhook when the render completes. Finished media is copied to INFRO storage under your account, so output URLs keep working instead of expiring when the upstream cleans up.

Each organization starts with production, staging and development, and you can add your own. A gateway key belongs to exactly one environment; a connection or route can serve one, several or all of them. A key never reaches a connection outside its environment: the request is refused instead of crossing over.

Yes, from the Team plan. Send your customer's id in the X-INFRO-User-Id header or metadata.user_id, and set a daily, weekly or monthly cap per organization or project. At the cap the gateway returns 402 with code end_user_budget and resets_at, the time the cap resets, so your application can tell its user.

Studio is the platform's workspace for image, video and audio: a storyboard of scenes and shots, a cast, a Director that turns a brief into shots and prompts, export to Final Cut Pro, DaVinci Resolve and Premiere Pro, and team review. It is part of every plan, with no add-on and no new price. Every generation runs on your own provider connections, so your provider bills you for it directly; Studio shows the estimated provider cost before every run, and INFRO takes 0% of that spend.

Nothing until an owner or admin turns Studio storage on, which is recorded in the audit log. Then Studio keeps uploads, results and the prompt, model, provider and settings behind each one, for 30 days on Developer, Startup and Team, 90 days on Business and 1 year on an Enterprise agreement. Every item shows the date it is kept until, deleted items stay in Trash for 7 days, and downloads and exports are always available while an item is kept. Studio storage never turns on request payload logging.

Yes, from the Business plan. It puts INFRO between your agents and the MCP servers they use: GitHub, Linear, Sentry, Supabase, Stripe or your own internal tools. An admin registers each server once with its credential, approves its tools and grants them to gateway keys. Agents connect to one endpoint with the gateway key they already use for model calls. On every call INFRO adds the server's credential so the agent never holds it, serves only the tool definition an admin approved and refuses a tool whose definition has changed since, validates the arguments, applies your guardrails to the arguments and the result, and records the call on the same trace as the agent's model calls. INFRO never runs a tool or hosts a server, and tool calls are not priced or counted against your request allowance.

Yes, through the INFRO MCP server at mcp.infro.io/mcp. Claude and ChatGPT connect by signing in from the assistant: you choose one organization and what the assistant may do, and it acts with your own role. Claude Code, Codex, Cursor and VS Code can sign in the same way; Windsurf and scripts use a management token. The assistant can answer questions such as which model cost the most last week or why a request failed, and make a small set of changes you confirm, such as setting a spend limit. It never calls a model, never sees prompts or completions, and every change it makes is written to the audit log. Reading is included from the Startup plan; changes beyond projects and keys need the Team plan.

No, and we will not imply otherwise on a slide. What exists instead is published rather than promised, at /trust: a SOC 2 roadmap with an audit firm engaged and the observation window not yet scheduled, ISO 27001 marked under evaluation with no date committed, the controls that are enforced today alongside the ones that are not, and our answers to a standard security questionnaire as a document you can download without talking to us. The DPA with Standard Contractual Clauses, the subprocessor list and the acceptable use policy are published in full too. Send your own questionnaire anyway — we answer every question including the ones where the answer is not yet. If a certificate is a hard gate on your side, tell us at the start and we will say plainly that we cannot clear it today.

Infrastructure vendors are named at /subprocessors, with the notice periods and emergency exception explained there. You choose and contract directly with the AI providers you connect. Request traces identify the connections attempted; provider data use and retention follow your own agreements and account settings.

Yes, on an enterprise agreement: the subscription is invoiced quarterly or annually on your terms rather than charged to a card. That is an invoice for the software only. Model usage is invoiced to you by your own providers on whatever terms you already have with them, and no arrangement with INFRO changes that or puts it on an INFRO invoice.

You can, and plenty of teams do. It means three vendors, three dashboards, and the gaps between them — the router knows where a request went, the proxy knows what it looked like, and neither knows what it cost against your budget. INFRO is one layer doing the whole job: the request that was routed is the request that was traced, priced, and checked against your organization's policy. One integration, one place to look.