AI product
Text, image and video generation inside your own product.
We build generation into your product: pick the model for the task, write and tune the prompts, set up a job queue, result storage, limits and usage accounting. A new model plugs in by replacing one layer, with nothing else touched.
A fit when it is clear a model solves the problem but not how to get it into production: queues, cost, failures and the wait a user sees. Also a fit when the demo already exists and needs to become a product feature.
Where to start
You have a specification
Send the document by email. We answer with an estimate in hours, a deadline and the questions it leaves open.
Send it for an estimatehello@tok.moscowYou have no specification
We start by writing one. Questionnaire, a day of briefing, the document in two days, then the work is priced from it.
The Technical specification service- Working hours
- 100–220 hours
- Duration
- 35–75 days
- Hourly rate
- $480
- Price
- $48,000 – $106,000
Stages of work
Drag the edge of any stage. It changes width, the neighbours shift, and the deadline and price recalculate.
- Working hours
- Duration
- Price
- 01Test the hypothesis on your data
- 02Pipeline and model selection
- 03Interface, limits, billing
- 04Load, monitoring, handover
Hypothesis tested on your data; Model selection and prompts; Job queue and result storage; Limits, usage accounting and billing; Generation interface; Monitoring and handover of rights.