The variant treadmill
Every channel wants five headlines, three lengths and a localised version. Your team writes the same idea forty times a week.
For marketing teams
More campaigns, less blank page
Headlines, ad variants, SEO briefs, landing page drafts and social calendars. Get strong first drafts in seconds and spend your craft on the final polish.
Variants on tap
ad and subject-line options in seconds
Cost per asset
every draft shows what it cost
On-brand drafts
your voice guide in every prompt
The problem
What is slowing you down today
Tool sprawl
A writing tool here, an image caption tool there, each with its own seat licence and none talking to your stack.
Spend you cannot attribute
You know AI helped the campaign. You cannot say what it cost per asset or per launch.
Capabilities
Everything you need, nothing you don't
Bulk variant generation
Send your brief and voice guide as the prompt and get headline, body and CTA options back in one call.
Right model for the job
Use chat models for everyday copy and pin a named model when a hero launch deserves your favourite.
Price per asset
Each response shows tokens and price, so you can report what a campaign's drafts actually cost.
Repeat briefs from cache
Run the same brief again within the cache window and it comes straight back, unbilled.
Plug into your stack
One HTTP endpoint fits your CMS, your automation tool or a simple script your ops lead maintains.
Shared playground
Marketers test prompts in the browser before anyone writes a line of integration code.
Use cases
What teams run on it
01
Ad copy variants
Headlines and descriptions sized for each placement, ready for your next A/B test.
02
SEO content briefs
Outline, search intent, questions to answer and internal link ideas from a keyword and a URL.
03
Email subject lines
A dozen subject lines and preview texts per send, in your brand voice.
04
Social calendars
A month of post ideas per channel, drafted from your campaign theme and key dates.
How it works
From sign-up to production
- 1
Draft in the playground
Paste your voice guide and brief, compare models and keep the prompt that sings.
- 2
Connect your tools
Have ops wire the endpoint into your CMS or automation platform with one API key.
- 3
Scale the calendar
Generate at campaign volume and watch spend in the usage dashboard as you go.
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
Do I need a developer to start?
No. The playground runs in the browser. When you want automation, one HTTP call is all a developer needs to wire up.
Can it keep our brand voice?
Include your voice guide and examples in the prompt. Every call works from exactly what you send.
How do I know what a campaign cost?
Each response includes its price, and the usage dashboard shows daily and month-to-date totals.
Is there a free way to try it?
Yes. Every account includes a free monthly token allowance.
Fill the calendar before Friday
Start drafting in the playground, free. Scale when the campaign does.