Every price, on one page
Fixed prices in US dollars. Every package starts with a paid first step, and its fee is credited to the build if you go ahead within 30 days.
Scoping sprint
A written assessment with acceptance criteria, a proof on your own data where the package allows it, and a fixed quote for the build. The fee is credited to the build if you go ahead within 30 days.
$1,200–$1,500
3–5 business days
| Package | First step | Build | Time |
|---|---|---|---|
| Model-retirement migration sprint For teams whose code calls models that shut down between November and January. | $1,200 Migration audit | $2,500 $1,500 for a single endpoint | 5 business days |
| Custom GPT migration For ChatGPT Business and Enterprise workspaces with custom GPTs people rely on. | $400 Inventory and migration plan | $1,200 Up to 3 GPTs; +$400 for each GPT with a custom action | 3 business days |
| Assistant that cites or refuses For teams whose assistant answers from internal documents and gets it wrong. | $1,200 Single-source starter | $3,000 $1,200 single-source starter (up to 50 documents, 5 days) | 10 business days |
| Document extraction pilot For firms re-typing invoices, leases, tax forms, rate confirmations or rent rolls. | $750 Proof on 10 documents | $1,500–$2,800 Depends on document type and how much the layouts vary | 5–10 business days |
| LLM cost and latency reduction For products and teams whose model spend is rising faster than usage. | $1,500 Cost audit | $1,500 audit $3,500 implementation | 1 week audit; 1–2 weeks implementation |
| Architecture and readiness review For founders and teams who want an independent review before or after building. | The review is the first step | $1,200–$1,500 | 3–5 business days |
| Agent reliability and evals harness For teams running agents or LLM features without automated tests, or losing OpenAI Evals on November 30. | $1,200 Baseline and plan | $2,000–$3,500 | 1 week |
| Workflow automation (n8n, Claude, MCP) For owners connecting email, CRM, documents and AI, and finding the joins break. | $950 Two-day repair | $2,200 $950 two-day repair of a broken n8n, Postgres or MCP setup | 5–10 business days |
| Financial data assistant (text-to-SQL) For finance teams, advisers and fintechs who want answers from their own database. | $1,500 One-week prototype | $4,500 $1,500 one-week prototype on a replica | 10–15 business days |
| Inbound voice agent A variant of workflow automation: answer, qualify, book and hand off. | Scoping sprint | From $4,500 | Set in the scope |
Terms, in plain English
Fixed price
The price in the written scope is the price you pay. If the work takes longer than we estimated, that is our cost.
Payment
First steps are paid up front. Builds are 50% to start and 50% on acceptance, or by milestone for longer work. Invoiced by Destello AI Incorporated in US dollars, payable by ACH or card.
Acceptance
Acceptance criteria are agreed in writing before work starts. The second payment is due when they're met.
Credit
The fee for a first step is credited in full to the build if you go ahead within 30 days.
Not included
Model-vendor API usage, third-party licenses and hosting are billed to your own accounts, so you see them directly.
Marketplaces
If we met through a freelance marketplace, the engagement stays on that marketplace under its terms.
Tell us what you have and what is going wrong.
A 20-minute call, then a written scope with acceptance criteria and a fixed price within one business day. If it isn't a fit, we'll say so on the call.
Or email hello@destello.us or call (628) 202-5322. We reply within one business day.