One API key for 30+ leading AI models with transparent billing
OpenAI-compatible router that puts free LLM models from 13 providers behind one endpoint with automatic failover
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
FR
Pricing model
Paid
Freemium
Pricing
Prices vary by model. Vergora offers up to 90% off list prices compared to official provider rates. Users can top up flexibly with Apple Pay or Visa in small amounts.
Free: open core under BSL 1.1, no account or card required. Pro: 12 € monthly (or 9.08 € per month billed annually at 109 €/yr), or 199 € for Lifetime license (one payment, no renewals, limited to first 200). 14-day free trial for Pro requires a card.
Key features
Access to 30+ AI models including GPT, Claude, Gemini, DeepSeek
Single API key for all supported models
Per-request billing with token, latency and cost transparency
Chat and reasoning models
Code workflow support with model selection
File understanding capabilities
Image generation models
Support for long-running agents
Flexible top-up with Apple Pay or Visa
Request identifiers and usage records for troubleshooting
Automatic failover across 13 free LLM providers
OpenAI-compatible API endpoint
Model capability testing for tools, JSON and vision
Hardcoded zero paid model fallback
Local router with keys staying on your machine
Model fusion and answer synthesis in Pro
Custom virtual model profiles in Pro
Native prompt compression to reduce tokens
Automatic model cooling and recovery probing
Support for Cursor, Continue, Open WebUI, LangChain and Claude Code
What makes it different
Up to 90% savings off official list prices for supported models
Keep existing API request format by swapping endpoint and model ID
Transparent per-request billing showing exact cost before calling
One unified account and API key across multiple model providers
Searchable model catalogue with filters and sortable pricing comparison
Structured inability to spend money on paid models, enforced in code not configuration
No middleman: keys stay local, prompts go directly to providers
Benchmarked quality parity with gpt-5 for classification, extraction and reasoning
Millisecond failover when a model rate-limits or fails
Vergora
Ficelle