A 4B model that estimates numbers from text with calibrated intervals
Stage
Not given
Not given
Founded
Not given
Not given
Based in
HK
Not given
Pricing model
Paid
Freemium
Pricing
Usage-based billing with prepaid balance; selected models available at launch discounts up to 91%. Example prices: GPT-6 Astra $0.9 input / $4.5 output per 1M tokens (−91%), Claude Opus 5 $1.4 input / $7 output per 1M tokens (−72%), Gemini 3.1 Pro Preview $0.8 input / $4.8 output per 1M tokens (−60%
First 1,000 estimates free. Pricing for additional estimates available upon request.
Key features
One API key for LLM, image, video and music models
OpenAI-compatible API endpoints
Anthropic-native and Gemini-native protocols
Claude Code, Cursor and Cline integration
Asynchronous image, video and music generation
Unified usage dashboard and request logging
Launch discounts up to 91% on selected models
No monthly subscription, prepaid balance only
Access to 15 AI providers and 57+ models
Multi-region automatic failover
Returns median, quantiles, and calibrated intervals for numerical estimates
Processes text records in a single forward pass without text generation
Responds in approximately 160 milliseconds
Flags when targets are outside training distribution or intervals lack calibration guarantees
Supports few-shot learning with at least eight labeled examples
Trained on 36 public sources
Calculates probability of exceeding user-specified thresholds
For count targets can return probability of each whole number
Accepts text input without requiring schema declaration or preprocessing
Costs roughly two orders of magnitude less per prediction than frontier models
What makes it different
One API key and prepaid balance for multiple providers and modalities
Transparent pricing with launch discounts up to 91% vs official prices
Same model guarantee without silent replacement or quantizing
Built-in support for coding agents and agent frameworks
Unified usage tracking and audit trail across all models and modalities
Provides calibrated uncertainty quantification where language models cannot
Transparently reports when calibration guarantees are absent
Dramatically faster inference than text-generating alternatives at 160ms
Designed for unstructured text without requiring labeled training data
Explicitly signals new, unseen targets with fallback capability for code
OmniaKey
maap