| What it does | OpenAI-compatible router that puts free LLM models from 13 providers behind one endpoint with automatic failover
| Uncensored open-weight models over OpenAI- and Anthropic-compatible APIs
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | FR
| Not given
|
|---|
| Pricing model | Freemium
| Paid
|
|---|
| Pricing | 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.
| GLM-5.3 Flash Abliterated: $0.0977 per 1M input tokens, $0.3421 per 1M output tokens, $0.0098 per 1M cached input tokens. DeepSeek V4.1 Flash 1017: $0.27 per 1M input tokens, $1.08 per 1M output tokens, $0.0054 per 1M cached input tokens. GLM-5.3 Flash (stock): $0.135 per 1M input tokens, $0.45 per
|
|---|
| Key features | - 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
| - Abliterated language model (GLM-5.3 Flash Abliterated) with refusal behavior removed from weights
- 14 stock models including DeepSeek, GLM, Kimi, Ember, and others
- OpenAI-compatible API endpoints for integration with tools like Pi, Claude Code, Cursor, and Cline
- Pay-per-token billing with no subscription or minimum spend beyond $5 top-up
- Prepaid credit that never expires
- Zero data retention of prompts and outputs
- Support for multiple payment methods: card (Whop) and cryptocurrency (Monero, Bitcoin, USDT, Ethereum, Litecoin)
- Anonymous account creation with 16-digit account number, no KYC required
- Text and image input support on multiple models
|
|---|
| What makes it different | - 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
| - Lowest-priced uncensored GLM-5.3 Flash variant at $0.0977 per 1M input tokens and $0.3421 output
- Refusal behavior removed at the model weight level, not through prompting
- Crypto payments without KYC and zero data retention
- $0.50 free trial credit for every new account with no initial payment required
- 18+ only platform with content policy aligned toward fewer refusals
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 1 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 6 |
|---|
| Citation Flow (Majestic) | 12 | 19 |
|---|
| Referring domains (Majestic) | 1 | 4 |
|---|
Ficelle
AbliteratedLLM