Estimate cost
estimateWhat a piece would cost and whether it can launch, BEFORE anything is spent — the same verdict the human cockpit shows. Accepts the same arguments as project creation (idea, format, source, cast, production). $0, no LLM.
The answer has two parts: launch.ready says whether the REQUEST is complete and allowed (launch.blockers names what is missing); economics says what it costs and whether the wallet governs it: estimateUsd (typical) with estimateMinUsd/estimateMaxUsd (a band, not a quote — production charges what it actually spends), walletBalanceUsd, and reason, one of: guard_inactivo — billing is not active in this environment: no wallet governs the launch. · saldo_desconocido — the wallet balance could not be read; nothing is inferred from that. · pedido_sin_cotizar — not enough to price yet: the request needs an idea (prompt_seed or source) and a duration_profile (or the platform default). · alcanza — the wallet covers the estimated band. · casa_invita — first piece of this account: the balance does not govern it; the band is informational. · excede_bienvenida — first piece of this account, and this request is above what a first piece can be: a shorter duration profile or no presenter fits — price the change with estimate. · operador_de_la_casa — this credential belongs to a platform operator: production is not charged to this wallet; the band is informational. · no_alcanza — the organization's balance does not cover the estimated band. economics.applies is true only when the wallet does not cover the request; estimateMaxUsd against walletBalanceUsd is what decides whether a real wallet covers the piece; hint restates the reason in words. WHERE THE LINE STOPS FOR FUNDS: the script (first station) is written before the balance is checked and settles with the first render; the first station that checks the balance is the studio build, then the final render — if the balance does not cover a station the line stops there (the project status reports waitingForFunds with the station) and what was already produced stays. vocabulary in the answer glosses every typed value that is not English.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cast | No | The cast, as at creation. A presenter on screen (`face`, `on_camera` or `describe_face`) moves the price. | |
| source | No | The creator's OWN material. `kind=script` + `respect=strict`: the piece narrates the text verbatim (word-level control from the start); `kind=content`: an article or notes the Director adapts (`respect` guided|adaptive). Without it the Director writes from `prompt_seed`. | |
| material | No | The creator's own uploaded files that belong to this piece (footage, photos, a recorded voice). Each item names one file of the personal library by its `assetId`: the id alone, or an object with `asset_id` and a `purpose` (what the file is for in the piece). The files are stored with the piece; the answer says what the piece does with them (`direction`), and they are not part of the price. While a file is still being verified, the `handle` of its upload is accepted in place of the id, and the request is answered as not ready; a file that is not in the caller's library is answered as not usable. | |
| production | No | ||
| references | No | The addresses the creator pointed to, each with the role they give it, apart from the idea. `parecido_a_este`: a video or page whose FORM the piece resembles (pace, tone, format); it is not read as a source of facts and does not close the corpus. `fuente`: the facts come from there; it is read as primary material, like a URL in `prompt_seed`. `otra`: neither is certain; it is read as primary material, as any URL of the request is. The writers receive each one with its role. | |
| prompt_seed | No | The idea (the same field as at creation). Optional here: without an idea or a `source` the verdict says `no_idea` and there is no price yet. | |
| target_language | No | ||
| creative_referent | Yes | A referent id from Vixdeo's catalogue of formats. |