GitHub (Calcium-Ion/new-api)
Measured metrics
- Overall score
- 8.3 / 10 ★★★★
- Stability band
- Poor
- Uptime
- 77.05% （Measured here）
- Response latency
- 1429 ms
- Model count
- Not detected
- Backend engine
- new-api
- Verification
- Verified
- Last checked
- 2026-10-01
- Outbound clicks
- 59 clicks
Uptime basis: Measured here, from 61 valid checks over the last 30 days, per-day reachability (not per request). The resolution is one day — 77.05% means roughly 7 unreachable days out of 30.
About this service
A globally hosted relay that fronts a range of AI model APIs. It covers the Claude, GPT, Gemini, DeepSeek families. Backend engine: new-api. Check that the host is reachable from your network before committing.
Strengths
- Overseas-hosted, so no China-specific network restrictions
- Built on new-api, a widely deployed gateway codebase
- Marked as verified by this site
Watch out for
- Check reachability from your own network before committing
- No /v1/models endpoint has been confirmed — verify before integrating
Model families supported
Daily monitoring log
| Date | Uptime | Avg latency | Samples | Status |
|---|---|---|---|---|
| 2026-10-27 | 100.00% | 1429 ms | 1 | 200 |
| 2026-10-26 | 100.00% | 1672 ms | 2 | 200 |
| 2026-10-25 | 100.00% | 1633 ms | 2 | 200 |
| 2026-10-24 | 66.67% | 9345 ms | 2 | 200 |
| 2026-10-23 | 33.33% | 3563 ms | 2 | — |
| 2026-10-22 | 100.00% | 1579 ms | 2 | 200 |
| 2026-10-21 | 66.67% | 8823 ms | 2 | 200 |
| 2026-10-20 | 100.00% | 2784 ms | 2 | 200 |
| 2026-10-19 | 33.33% | 4935 ms | 2 | — |
| 2026-10-18 | 100.00% | 2237 ms | 2 | 200 |
| 2026-10-17 | 100.00% | 8295 ms | 2 | 301 |
| 2026-10-16 | 100.00% | 1871 ms | 2 | 200 |
| 2026-10-15 | 66.67% | 8819 ms | 2 | 200 |
| 2026-10-14 | 33.33% | 4884 ms | 2 | — |
Data sources
awesome-ai-api public dataset (daily automated probing of /v1/models and host reachability)
We are not affiliated with GitHub (Calcium-Ion/new-api) and do not act as its agent, and we do not vouch for its service or the safety of your funds. Figures may lag or contain errors — if you spot one, please report it.
Similar services
Avian
Per the service's own site: Fast AI inference billed per token. DeepSeek V3.2, Kimi K2.5, GLM-5.…
apipro.maynor1024.live
An overseas AI API relay and aggregation service. Model coverage spans Claude, GPT, Gemini. It e…
api.cursorai.art
A globally hosted relay that fronts a range of AI model APIs. Claude, GPT and other families are…
LLM Gateway
The site itself puts it this way: Route, manage, and analyze LLM requests across OpenAI, Anthrop…
MegaLLM
Per the service's own site: The reliable AI gateway for developers. Access GPT-5, Claude Opus 4.…
Requesty
Its own site describes it as: Route every LLM call through one OpenAI-compatible API. Claude, GP…