PrivateDeskAI Gateway

OpenAI-compatible LLM inference gateway with automatic failover.

First two providers (both lines): a decentralized inference network Standard third provider: an insurance provider outside that network; Super Deal: all four in that network Model: DeepSeek-V4-Flash-0731

Independent monitoring

94.4%Availability, last 24 hours

94.4%Good answers, last 24 hours

3.22 sTime to first text, median

Median of the other providers (8): availability 93.6%, good answers 89.7%, time to first text 3.65 s.

Updated 2026-11-12 18:00 UTC. Source: power.gnk.space.

Good answers, independent monitor power.gnk.space, last 7 days (higher is better). ━━ SAGG ╌╌ median of the other providers

Measurements of the independent monitor Gonka Space (power.gnk.space), model DeepSeek-V4-Flash, tariff Super Deal. SAGG stands outside the main list in this monitor. These are measurements for the stated period, not a promise. History.

Second monitor: G-Meter

9.1%Failed probes, latest quick run (1 of 11)

11.5 sLatency of the run

23 t/sOutput speed

Median of the other brokers (11, latest quick runs): failed probes 16%, latency 9.0 s.

Run started 2026-11-12 16:10 UTC. Source: G-Meter, Gonka Labs.

Failed probes, G-Meter (Gonka Labs), last 7 days (lower is better). ━━ SAGG, quick runs ◇ SAGG, limits runs ╌╌ median of the other brokers Each dot is one run; diamonds are limits runs.

Probe results of the public monitor G-Meter (Gonka Labs, meter.gonka.gg) for the SAGG broker, as published, including provider-side errors such as 503. Nothing is filtered or smoothed. These are measurements for the stated period, not a promise. History.

Why PrivateDeskAI

SAGG routes every request across up to four independent inference providers in a fixed order, with automatic failover the moment one is degraded or unreachable. You get a single stable API, not a dependency on any one upstream provider's uptime.

Reliability is enforced in the gateway itself, not left to chance:

Per-provider circuit breakers isolate a failing source automatically, based on its live error rate.
You pay only for what you receive. A dropped stream is not billed twice, and an answer that could not be delivered costs nothing.

Date of this measurement: 23-24 October 2026 (version R1). The gateway has changed since then; current figures are in the independent monitor above and on the status page.

Measured on version R1 over 24 hours (2026-10-23 to 2026-10-24, synthetic set of five request classes): Standard served 99.94% of requests (4,769 of 4,772), median time to first text 1.4 s, 95th percentile 7.7 s. Super Deal (economical tariff, depends on one decentralized inference network, no insurance outside it) served 98.82%, 95th percentile 6.9 s. Billing matched delivery with no discrepancy. One day is a measurement of that day, not a promise. Method, data and limits: benchmarks.

Methodology and complete raw data: github.com/privatedeskai/sagg-benchmark-data. Full breakdown: /benchmarks.

Live status

Checking...

Links

API documentation Compatibility Status /models Privacy Terms Acceptable use Refunds Support Security

Get API Key