A typed decision API for routing, classification, and scoring
Stage
Not given
Not given
Founded
Not given
Not given
Based in
DE
CA
Pricing model
Freemium
Paid
Pricing
Free: up to 200 source texts. Hobby: €12/month for up to 2,000 source texts (14-day trial). Pro: €45/month for up to 10,000 source texts (14-day trial). All plans include unlimited translations and target languages.
$0.040 USD per million input tokens; output is free
Key features
Integrates with Angular, React Intl, Android, Flutter, GitHub Actions, and IntelliJ IDEA
Preserves file structure, formatting, placeholders, and existing translations
Context-aware translations using existing translations for terminology and style
One synchronous API request returns translated files in same build or CI run
Repository remains the source of truth with no platform setup required
Pricing based on unique source texts, not per-translation or per-language
30-day money-back guarantee for paid plans
Choice question type with multiple options and probability scores
Boolean question type for true/false judgments with probability
Score question type with min/max range and level probabilities
Filter list endpoint for ranking JSON items by instruction match
Support for image and audio input with Crossroads-M model
Idempotency keys for safe retries without duplicate charges
Rate limiting with 120 requests per minute default and 4 concurrent requests
Multiple question types per request with single round trip
What makes it different
Repository-native: keeps localization files in version control without forcing a new platform
On-demand: returns translated files in the same script or CI pipeline run with no project queue
Works with files already in your repository without requiring translators to leave their workflow
Built and maintained by a single founder focused on developer tooling
Returns probability scores for every answer to guide decision-making confidence
Supports image and audio analysis alongside text with dedicated audio-trained model
Filter lists by instruction match without writing text generation code
Typed output constrains format while preserving flexible judgment logic