| What it does | One API for 100+ language models including GPT, Claude, Gemini and DeepSeek
| 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 | SG
| FR
|
|---|
| Pricing model | Paid
| Freemium
|
|---|
| Pricing | Pay-as-you-go with 0% platform fee. Qwen, DeepSeek, GLM and Kimi from $1.4 per million tokens. GPT-6 input from $0.08 per million tokens. Images from $0.03 per image, video from $0.04 per second.
| 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 100+ language models from GPT, Claude, Gemini, DeepSeek, Kimi, Qwen, GLM and other providers
- Image and video generation from multiple providers
- Automatic fallback and provider-level routing
- Budget controls and usage monitoring per API key or user
- Cost, error rate, latency and fallback frequency alerts
- Integration with AI coding tools including Claude Code and Cline
- Global edge nodes for low-latency access
- Pay-as-you-go billing with no platform fees
- Non-expiring balance and no minimum spend
| - 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 | - Single API key for 100+ models eliminates account and billing fragmentation
- Zero platform fees with billing at each provider's official rates
- Drop-in replacement with no SDK changes required
- Automatic fallback and failover across model providers
- Non-expiring credits with no subscriptions or minimum spend
| - 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
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 47 ▼ −1 (down) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 25 | 0 |
|---|
| Citation Flow (Majestic) | 44 | 12 |
|---|
| Referring domains (Majestic) | 807 | 1 |
|---|
OfoxAI
Ficelle