Thin product pages
Thousands of SKUs with a one-line description from the spec sheet. Shoppers bounce, search engines shrug.
For retailers and online stores
A whole catalog, beautifully described
Product descriptions for every SKU, review summaries shoppers trust, support replies that resolve on the first touch, and merchandising copy for every season.
Every SKU covered
descriptions generated at catalog scale
Cost per product
price reported on every call
Peak-ready
fail-over through big sale days
The problem
What is slowing you down today
Reviews nobody reads
Shoppers want the gist. Your top products have hundreds of reviews and no summary.
Peak-season support
Where is my order. Can I return this. The same questions, ten times the volume.
Capabilities
Everything you need, nothing you don't
Bulk product descriptions
Turn attributes and spec sheets into on-brand copy, with titles and bullet points per channel.
Review summaries
Condense reviews into pros, cons and who the product suits.
Support reply drafts
Draft answers from your returns and shipping policies for agents to send.
Lowest-priced fit
Catalog copy rarely needs your heaviest model. The router picks the lowest-priced model with the capability.
Cache on repeat prompts
Re-running an identical prompt inside the cache window returns instantly and is not billed.
Steady on sale days
Automatic fail-over keeps support assist working when traffic spikes.
Use cases
What teams run on it
01
Catalog enrichment
Descriptions, bullet points and meta copy for every SKU.
02
Review highlights
A short summary block on each product page.
03
Order and returns support
Policy-grounded reply drafts for your help desk.
04
Seasonal merchandising
Collection intros, gift guides and promo banners.
How it works
From sign-up to production
- 1
Describe one product
Paste attributes into the playground and tune the voice.
- 2
Batch the catalog
Loop through SKUs with an API key and an Idempotency-Key per item.
- 3
Watch spend as you go
Daily and month-to-date usage in the dashboard.
Control
Built so you stay in charge
Keys you control
API keys are shown once at creation and stored only as a hash. Revoke any key instantly from Settings.
Spend you can see
Every request carries its own receipt: tokens in, tokens out, latency and price. Nothing is billed that you cannot trace.
Limits you set
Per-account rate limits and a free monthly allowance keep experiments safe before they become production.
Data you decide on
You choose exactly what you send. Repeat prompts can be served from your cache, and cache hits are never billed.
For developers
One endpoint. Every model.
Send a prompt and a capability, or name a model. One bearer key, one small JSON body, and a full receipt on every response.
curl https://YOUR-DOMAIN/api/ainf/inference \
-H "Authorization: Bearer $AI_INFERENCE_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: order-1042" \
-d '{"prompt":"Summarise this ticket in one line","capability":"chat"}'Questions, answered
Can I generate thousands of descriptions?
Yes. Loop through your catalog against one endpoint. Your account's rate limit sets the pace, and you can adjust it in settings.
How do I avoid paying twice if a batch restarts?
Send an Idempotency-Key per item. Usage for a key is metered once.
Will it invent product features?
Give it your real attributes and ask it to use only those. Review high-traffic pages before publishing.
What will my catalog cost?
Each response reports its price, and the catalog shows per-token prices for every model, so you can estimate from a sample.
Give every product the page it deserves
Start describing your catalog on the free allowance.