• Unified API
  • Mobile SDK
  • Connection Widget
  • Streaming
  • Lab Reports API
  • Graph API
  • Health Scores
  • Health Rewards
  • Planned Workouts
  • Predictions
  • Lab Testing
  • AI Interface
  • Enterprise
  • Insurance
  • Integrations
  • Research
  • Podcast
  • Blog
  • Reports
  • Events
  • Documentation
  • Community
  • Example apps
  • Wearable Data
  • About
  • Customers
  • Partners
  • Careers
  • Support
  • Pricing
Terra
Pricing
Become an integrationGet started

Health predictions across 100+ wearables and apps

From the wearable and app data you already receive: sleep schedules, cycle phase, activity patterns, and the readings a device never took.

Run predictions over health data you already receive through Terra API

Different predictions help you understand and predict various events in your users’ health and fitness: activity patterns, menstrual cycle, sleep and lifestyle habits.

1
Choose your prediction and run it across selected users
A prediction reads the data Terra already sends you and works out what the device never captured. Pick the area you want, sleep, daily or activity, and choose the users to run it over. Each area unlocks its own set of new metrics, and your existing integration stays exactly as it is.
Choosing sleep, daily or activity data to unlock new metrics for
2
Know how much more you can get, user by user
Every device records a different slice, and a user who leaves their watch off overnight widens the gap further. Before you commit a feature to a metric, you can see how much of a user's history was actually recorded and how much a prediction would add on top of it.
How much of a user's health history is recorded and how much can be predicted
3
Every value says whether it was measured or predicted
A predicted value comes back in the same field and the same units as a recorded one, flagged as predicted and carrying a confidence tier. Show measurements plainly, caveat the predictions, and gate the rest, so every value a user sees is labelled for what it is.
A sleep record with recorded and predicted values marked separately

Predictions your product can act on, without building a research team

Three predictions are generally available today. Each returns a structured answer you can render directly, so the feature is a render away, and the science behind it is already published.

Foresee sleep changes

The bedtime and wake time a user should keep, predicted from the rhythm they already hold. Comes back with a consistency score from 0 to 100, a plain-language band, and the single change that would move it up.

Predict cycles

Cycle phase for every day in a range, with period onsets and fertile windows read from overnight physiology alone. The user logs nothing, and a day you have already shown stays fixed. Intended for wellness use only.

Infer missing data

The measurements a device never took, predicted from the channels it did capture and from the user’s own history. Every field is marked as recorded or predicted and carries a confidence tier, so you never show an estimate as a measurement.

A prediction catalogue that keeps growing

Sleep, women’s health and gap-filling are live now. Activity patterns, apnea screening, cycle anomalies, fragmented nights and metabolic health are moving through validation with design partners, and the research behind each one is published as it lands.
01

Sleep schedule

Generally available. The bedtime and wake time a user should keep, with a consistency score and the single change worth making.

Browse the research
Sleep schedule
02

Menstrual cycle

Generally available. Cycle phase for every day, with period onsets and fertile windows predicted from overnight physiology alone.

Browse the research
Menstrual cycle
03

Missing readings

Generally available. The measurements a device left out, predicted from the channels it did capture, each field marked recorded or predicted.

Browse the research
Missing readings
04

Activity patterns

In validation. Repairs the activity type a user mis-tagged, reads the training intent behind a run, and surfaces workouts that were never logged at all.

Browse the research
Activity patterns
05

Cycle anomalies

In validation. Flags sustained disruption to a user's established cycle rhythm, with an alert level that escalates the longer it persists.

Browse the research
Cycle anomalies
06

Sleep apnea risk

In validation. A per-night risk reading and a user-level score from overnight data. Intended for wellness use only.

Browse the research
Sleep apnea risk
07

Fragmented nights

In validation. Regroups the sessions a device split across one night back into the single night they belong to, so a broken night reads as one.

Browse the research
Fragmented nights
08

Metabolic health

Metabolic trends read from the signals a wearable already records, for products built around weight, energy and long-term health.

Browse the research
Metabolic health
09

A prediction for your use case

Bring the research team a question your data could answer and we will tell you whether it is tractable.

Browse the research
A prediction for your use case
01

Sleep schedule

Generally available. The bedtime and wake time a user should keep, with a consistency score and the single change worth making.

Browse the researchSleep schedule
02

Menstrual cycle

Generally available. Cycle phase for every day, with period onsets and fertile windows predicted from overnight physiology alone.

Browse the researchMenstrual cycle
03

Missing readings

Generally available. The measurements a device left out, predicted from the channels it did capture, each field marked recorded or predicted.

Browse the researchMissing readings
04

Activity patterns

In validation. Repairs the activity type a user mis-tagged, reads the training intent behind a run, and surfaces workouts that were never logged at all.

Browse the researchActivity patterns
05

Cycle anomalies

In validation. Flags sustained disruption to a user's established cycle rhythm, with an alert level that escalates the longer it persists.

Browse the researchCycle anomalies
06

Sleep apnea risk

In validation. A per-night risk reading and a user-level score from overnight data. Intended for wellness use only.

Browse the researchSleep apnea risk
07

Fragmented nights

In validation. Regroups the sessions a device split across one night back into the single night they belong to, so a broken night reads as one.

Browse the researchFragmented nights
08

Metabolic health

Metabolic trends read from the signals a wearable already records, for products built around weight, energy and long-term health.

Browse the researchMetabolic health
09

A prediction for your use case

Bring the research team a question your data could answer and we will tell you whether it is tractable.

Browse the researchA prediction for your use case
The insight library

The most comprehensive suite of health predictions

Every prediction answers in the canonical Terra schema with its confidence attached, so you can gate what you show on how far it will actually commit.

  1. Recommended bedtime
  2. Daily cycle phase
  3. Value provenance
  4. Recommended wake time
  5. Period onset
  6. Per-field confidence
  7. Time in bed
  8. Fertile window
  9. Predicted sleep fields
  10. Sleep regularity index
  11. and more…
  12. Ovulation crossing
  13. Predicted daily fields
  14. Regularity band
  15. Daily confidence band
  16. Predicted activity fields
  17. Schedule shift
  18. Detected onsets
  19. Device field coverage
  20. Projected regularity gain
  21. Cycle regularity
  22. History depth
  23. Approximation flag
  24. Projected onset
  25. VO₂max (run)
  26. Night reconstruction
  27. Forecast interval
  28. VO₂max (ride)
  29. Sessions per night
  30. Projected fertile window
  31. VO₂max (resting HR)
  32. Inter-session gaps
  33. Temperature path
  34. Confidence grade
  35. Device awakenings
  36. Per-day availability
  37. Improvement guidance
  38. Night assignment
  39. Nightly apnea risk
  40. Max heart rate
  41. Nap classification
  42. Apnea risk score
  43. Sessions analysed
  44. Activity classification
  45. Cycle anomaly flag
  46. Clean segments
  47. Training intent
  48. Alert level
  49. Result status
next ventures
pioneer fund
samsung next
y combinator
general catalyst

The world's best health apps run on Terra data

Get started
ProductsIntegrationsAI InterfaceAuthenticationMobile DevelopmentDocumentationGraphAPIPredictions
DocumentationAPISDKQuickstartExample Apps
CommunityBlogResearchCommunityPodcastAuthorsGithub
CompanyAboutCareersCustomersBecome an IntegrationCookies PolicyGDPRPrivacy PolicyTerms of Purchase
© Terra API. 2026 — All rights reserved.

Cookie Preferences

Essential CookiesAlways On
Advertisement Cookies
Analytics Cookies

Crunch Time: Embrace the Cookie Monster Within!

We use cookies to enhance your browsing experience and analyse our traffic. By clicking “Accept All”, you consent to our use of cookies according to our Cookie Policy. You can change your mind any time by visiting out cookie policy.

Cookies Policy