Multi-model AI API platform for accessing text, image, and video models through one account and API key
A typed decision API for routing, classification, and scoring
Stage
Not given
Not given
Founded
Not given
Not given
Based in
HK
CA
Pricing model
Paid
Paid
Pricing
Usage-based billing in USD with no monthly fee or subscription. Selected models are free to use. Discounts shown include up to 93.1% off on various models (Grok 4.6 at 93.1% off, GPT-6 Astra at 87.1% off, ClaudeCode at 70.1% off, Deepseek at 70.2% off, GLM at 70.1% off, Gemini at 81.1% off). Some mo
$0.040 USD per million input tokens; output is free
Key features
Access multiple AI models from different providers through one API key
OpenAI-compatible API integration
Codex and Claude Code compatibility
CC Switch setup tool for simplified configuration
Text, image, and video model generation
Usage-based billing with no subscription
Data security with no storage of prompts or responses
Referral rewards program with ongoing commissions
Support for models from ChatGPT, Claude, Gemini, Qwen, Deepseek, GLM and others
Unified account and consolidated usage tracking
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
One account and API key for models from multiple providers, eliminating separate account management
Unified billing and usage tracking in one dashboard across all models
No monthly subscription, only pay for actual model usage
Prompts and responses are never stored or used for training
Easy setup with OpenAI-compatible API and CC Switch configuration tool
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
LanoX
Crossroads