AI Proxy
China-Zone Relay · since 2023AI Proxy was a China-zone AI API relay provider offering OpenAI, Claude, and Gemini model forwarding. It supported HTTPS encrypted transmission and flexible billing. The service discontinued in June 2026 due to 502 errors and DNS issues. This page is preserved as a historical archive for developer reference.
This page aggregates AI API relay detection data for AI Proxy, focusing on whether Claude / OpenAI / Gemini are truly passthrough, whether usage fields are anomalous, whether model lists are usable, and accessibility across different network regions. If you're searching for "AI Proxy real or fake", "AI Proxy review", "API relay detection", or "relay price comparison", we recommend checking the detection summary, network status, and public pricing evidence below before deciding whether to continue using it.
Related:Relay Rankings · Price Comparison · Network Tools · FAQ · Buying Guide
/models endpoint. The provider may not support OpenAI-style model enumeration, may use a different endpoint path, or the current network probe failed. ✅ Strengths
- Stable access in China (during operation)
- Flexible billing, pay-as-you-go
- HTTPS encrypted transmission
- Covered OpenAI/Claude/Gemini mainstream models
⚠️ Notes
- Limited brand information, low transparency
- Model authenticity needs self-verification
- No public pricing page, login required
- Discontinued in June 2026, no longer available
🎯 Use Case
- Basic use cases for China-based developers
- Multi-model comparison testing environments
- Quick integration scenarios where pricing transparency is not critical
⚡ Speed Test from Your IP
🔬 Real Detection Summary
Last check: 2026-05-21 20:36 UTC
Recent Detection Latency Trend (30 times, old->new)
By Protocol
Last 5 reports
Source: All metrics from real detections after users submit API keys,Server-side Calls AI Proxy protocol verification requests from endpoints,. Pass rate = Requests returning correct responses / Total Requests。 -> Full Methodology
🛰️ System Probe Summary
The platform runs keyless connectivity probes every 6 hours on this site's OpenAI / Anthropic / Gemini protocol list-models endpoints (HTTP 401/403 counts as connected, indicating the endpoint is alive). Below are the cumulative real results.
⚠️ This site is marked as "discontinued". Endpoint unreachable is expected, not a quality signal.
By Protocol (System Probe)
Note: Connectivity rate = endpoint responses (incl. 401/403 auth responses) / probe count, measures endpoint liveness not service quality; service quality is determined by key-submitted detections in "Real Detection Summary" above.
📊 Real-time Detection Data
AI Proxy
0.0% Median Pass Rate · Snapshot Loaded💧 Water Rate v2 0.0 / 100 · Unavailable Real request http=200 ratio 0% Click to expand formula →
| Report | Protocol | Score | Duration | Time |
|---|---|---|---|---|
| View Report | OPENAI | 0% | 2026-05-21 20:36 | |
| View Report | OPENAI | 0% | 2026-05-18 18:00 | |
| View Report | OPENAI | 0% | 2026-05-18 18:00 | |
| View Report | OPENAI | 0% | 2026-05-17 18:00 | |
| View Report | OPENAI | 0% | 2026-05-17 18:00 |
📋 Protocol Suitability Matrix
Based on 14 real tests of protocol coverage and median pass rate, answering "Which protocols can I use with AI Proxy?"
| Protocol | Tests | Median Pass Rate | Status | Suggestion |
|---|---|---|---|---|
| openai | 14 | 0% | - Unknown | Test with small traffic first |
⏱ Rate Limits & Pricing Multiplier
Key operational parameters that determine whether you can scale concurrent calls.
⚠️ Actual multipliers depend on AI Proxy's backend account. This site does not directly hold account tokens and cannot see hidden SLAs.
🛠 Integration Tutorial: Get Started with AI Proxy in 3 Steps
- Register an account and create an API Key in the backend (the console usually has "My Keys" or "API Tokens" entry).
- Replace the base URL in your code with
https://api.aiproxy.io/v1, and select the model name from AI Proxy's list. - Test a request:
curl https://api.aiproxy.io/v1/v1/chat/completions -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" -d '{"model":"gpt-4o-mini","messages":[{"role":"user","content":"hello"}]}'
✅ This is an OpenAI Compatibility Mode integration example. Anthropic / Gemini protocols vary slightly by provider, see each site's documentation.。
❓ Frequently Asked Questions
Is AI Proxy reliable?
Based on 14 independent tests by TokenAPI Scan, the median pass rate is 0%.Low pass rate, test with small traffic first before production.
How much does AI Proxy cost?
AI Proxy does not have a public unified price list; log in to the backend for specific pricing. Compare similar sites on the Price Comparison Page for reference.
Which models does AI Proxy support?
AI Proxy's model list is not publicly enumerated yet; log in to the backend to view.
What's the difference between AI Proxy and official?
Official (OpenAI/Anthropic/Google) = first-hand pricing + stable direct connection + strict content moderation and account ban risk. Third-party relays = usually discounted pricing + domestic accessibility + but compounded availability, content moderation, SLA, and service shutdown risks. Which to choose depends on your cost sensitivity, content moderation requirements, and stability priorities. It is recommended to use official for critical paths + relays as backup.
Will AI Proxy shut down?
We continuously monitor relay site reachability. Multiple consecutive failed detections within 30 days = high risk signal. Recommendations: ① Don't top up too much ② Rotate across multiple providers for critical services ③ Watch the Rankings warnings.
💭 Related Questions
💰 Popular Model API Prices
Compare API prices across relay providers: