Live synthetic monitoring

TrustedRouter Status

Check TrustedRouter availability across regions with live gateway, attestation, SDK, billing, provider fallback, latency, incident history, and router-core uptime signals.

Last updated 2026-09-17T12:42:01Z

All Systems Operational

Router-core synthetic checks are passing for attested reachability, authorization, fallback, and settlement.

Operational · Router Core 99.99% Availability target In region gateway overhead p50: 174 ms Global observed gateway p50: 279 ms Latest synthetic sample 2026-09-17T12:40:25.000Z

Router Core

Attested TLS, authorization, route candidates, provider fallback, and settlement/refund durability.

Operational
Target 99.99% 5m uptime >99.99% 24h uptime 99.9568% 5m burn 0.0x

Control Plane

Dashboard, billing, key management, docs, and public status surfaces.

Operational
Target 99.99% 5m uptime >99.99% 24h uptime >99.99% 5m burn 0.0x

Gateway latency anatomy

Fresh connections include DNS, TCP, and TLS setup. Reused connections show the request path after that setup is paid once.

ConnectionEndpointRegion pathTotal p50DNSTCPTLSGatewaySamples
Fresh connection Global endpoint europe-west4 -> us-central1 67 ms 8 ms 1 ms 29 ms <1 ms 1
Fresh connection Global endpoint us-central1 -> us-central1 58 ms 9 ms 2 ms 9 ms <1 ms 2
Reused connection Global endpoint europe-west4 -> us-central1 2 ms paid once paid once paid once <1 ms 1
Reused connection Global endpoint us-central1 -> us-central1 3 ms paid once paid once paid once <1 ms 2
Fresh connection EU direct europe-west4 -> europe-west4 64 ms 30 ms 1 ms 10 ms <1 ms 1
Fresh connection EU direct us-central1 -> europe-west4 411 ms 39 ms 112 ms 119 ms <1 ms 2
Reused connection EU direct europe-west4 -> europe-west4 1 ms paid once paid once paid once <1 ms 1
Reused connection EU direct us-central1 -> europe-west4 112 ms paid once paid once paid once <1 ms 2
Fresh connection US Central direct europe-west4 -> us-central1 395 ms 33 ms 111 ms 119 ms <1 ms 1
Fresh connection US Central direct us-central1 -> us-central1 247 ms 45 ms 3 ms 9 ms <1 ms 2
Reused connection US Central direct europe-west4 -> us-central1 111 ms paid once paid once paid once <1 ms 1
Reused connection US Central direct us-central1 -> us-central1 3 ms paid once paid once paid once <1 ms 2
Fresh connection US East direct europe-west4 -> us-east4 327 ms 32 ms 88 ms 97 ms <1 ms 1
Fresh connection US East direct us-central1 -> us-east4 183 ms 40 ms 27 ms 32 ms <1 ms 2
Reused connection US East direct europe-west4 -> us-east4 89 ms paid once paid once paid once <1 ms 1
Reused connection US East direct us-central1 -> us-east4 26 ms paid once paid once paid once <1 ms 2

Upstream provider health

Continuously measured per provider from the rotation probe and real traffic over the rolling benchmark set of up to 10,000 samples. Ranked by success rate, then p50 TTFT. Unsupported route and probe-configuration rows are shown separately, not counted as provider downtime. This is an informational provider watch — a flaky upstream model does NOT count against router-core uptime above. Full leaderboard.

ProviderSuccessp50 TTFTError rateTop errorConfig excludedSamples
openai 100.00% 775 ms 0% — — 321
mistral 100.00% 812 ms 0% — — 58
cerebras 100.00% 1224 ms 0% — — 27
pearl 100.00% 1319 ms 0% — — 29
cloudflare-workers-ai 100.00% 1353 ms 0% — — 26
grok 100.00% 1478 ms 0% — — 33
google-vertex 100.00% 1541 ms 0% — — 25
together 100.00% 1549 ms 0% — — 108
mancer 100.00% 1610 ms 0% — — 28
confidential-ai 100.00% 1619 ms 0% — — 20
nscale 100.00% 1641 ms 0% — — 29
reka 100.00% 1653 ms 0% — — 22
inception 100.00% 1685 ms 0% — — 23
scaleway 100.00% 1785 ms 0% — — 28
engy 100.00% 1796 ms 0% — — 23
telnyx 100.00% 1804 ms 0% — — 26
deepseek 100.00% 1805 ms 0% — — 119
akashml 100.00% 1846 ms 0% — — 31
alibaba 100.00% 1885 ms 0% — — 27
zero-g 100.00% 1908 ms 0% — — 20
upstage 100.00% 1984 ms 0% — — 32
siliconflow 100.00% 1987 ms 0% — — 68
minimax 100.00% 2001 ms 0% — — 26
io-net 100.00% 2016 ms 0% — — 25
lightning 100.00% 2137 ms 0% — — 23
aion-labs 100.00% 2300 ms 0% — — 3
anthropic 100.00% 2346 ms 0% — — 80
thinkingmachines 100.00% 2399 ms 0% — — 31
wandb 100.00% 2414 ms 0% — — 21
scaledown 100.00% 2777 ms 0% — 6 provider_error 33
stepfun 100.00% 2789 ms 0% — — 32
azure 100.00% 2814 ms 0% — — 28
arcee 100.00% 2948 ms 0% — — 28
perplexity 100.00% 3037 ms 0% — — 41
makora 100.00% 3504 ms 0% — — 23
featherless 100.00% 3600 ms 0% — — 29
xiaomi 100.00% 3762 ms 0% — — 21
google-ai-studio 100.00% 4801 ms 0% — — 498
sakana 100.00% 6353 ms 0% — 11 router_error 22
kimi 100.00% 8270 ms 0% — — 128
zai 100.00% 8653 ms 0% — — 56
neurometric 100.00% — 0% — — 500
deepinfra 99.80% 3582 ms 0.2% provider_error — 493
fireworks 99.73% 3050 ms 0.3% provider_error — 373
tinfoil 99.44% 3927 ms 0.6% provider_error — 180
nebius 99.03% 3745 ms 1.0% provider_error — 103
baseten 98.78% 1221 ms 1.2% empty_output — 490
digitalocean 97.62% 2321 ms 2.4% TimeoutError — 42
sail-research 97.14% 2073 ms 2.9% TimeoutError — 35
relace 96.77% 2435 ms 3.2% TimeoutError — 31
nextbit 96.55% 1694 ms 3.5% provider_error — 29
openrouter 96.40% 10345 ms 3.6% provider_error — 500
regolo 95.45% 1675 ms 4.5% TimeoutError — 22
gmi 93.75% 3851 ms 6.2% TimeoutError — 16
friendli 93.33% 1355 ms 6.7% provider_error — 30
parasail 93.10% 2781 ms 6.9% provider_error — 29
atlas-cloud 93.10% 3363 ms 6.9% TimeoutError 1 probe_config_error 29
venice 90.91% 2430 ms 9.1% TimeoutError — 22
novita 89.74% 2827 ms 10.3% provider_error — 39
databricks 88.89% 1474 ms 11.1% TimeoutError — 27
wafer 88.46% 1764 ms 11.5% provider_error 1 unsupported_route 26
sambanova 86.67% 2783 ms 13.3% TimeoutError — 30
chutes 85.71% 7776 ms 14.3% TimeoutError — 28
inceptron 79.17% 2762 ms 20.8% provider_error — 24
morph 56.25% 1600 ms 43.8% provider_error 3 provider_error 32
nvidia-nim 48.39% 2528 ms 51.6% TimeoutError — 31
phala 47.06% 4367 ms 52.9% provider_error — 34
near-ai 0.00% — 100.0% provider_error — 25

Error budget burn

Burn rate means how quickly failures are spending the allowed error budget. Router Core is the paging signal. Upstream reliability is measured separately for every provider above.

Watch Router Core · 24h · 4.32x burn 2 bad / 4627 samples

Components

Each row is backed by live US/EU synthetic checks. Prompt and output content are not stored.

Operational Degraded Outage No data

Canonical API

api.trustedrouter.com attested TLS reachability and trust checks.

Operational
24h uptime 99.8948% Latency groups 4 Last check 2026-09-17T12:40:09.000Z
attestation_nonce · Global endpoint · europe-west4 -> us-central1 p50 1336 ms attestation_nonce · Global endpoint · us-central1 -> us-central1 p50 1227 ms tls_health · Global endpoint · europe-west4 -> us-central1 p50 279 ms tls_health · Global endpoint · us-central1 -> us-central1 p50 176 ms

US Central Regional API

US Central attested TLS reachability and trust checks.

Operational
24h uptime 99.9474% Latency groups 4 Last check 2026-09-17T12:40:08.000Z
attestation_nonce · US Central direct · europe-west4 -> us-central1 p50 1570 ms attestation_nonce · US Central direct · us-central1 -> us-central1 p50 889 ms tls_health · US Central direct · europe-west4 -> us-central1 p50 400 ms tls_health · US Central direct · us-central1 -> us-central1 p50 109 ms

US East Regional API

US East attested TLS reachability and trust checks.

Operational
24h uptime 99.8423% Latency groups 4 Last check 2026-09-17T12:40:08.000Z
attestation_nonce · US East direct · europe-west4 -> us-east4 p50 1224 ms attestation_nonce · US East direct · us-central1 -> us-east4 p50 941 ms tls_health · US East direct · europe-west4 -> us-east4 p50 301 ms tls_health · US East direct · us-central1 -> us-east4 p50 185 ms

EU Regional API

EU attested TLS reachability and trust checks.

Operational
24h uptime 99.9474% Latency groups 4 Last check 2026-09-17T12:40:09.000Z
attestation_nonce · EU direct · europe-west4 -> europe-west4 p50 910 ms attestation_nonce · EU direct · us-central1 -> europe-west4 p50 1457 ms tls_health · EU direct · europe-west4 -> europe-west4 p50 81 ms tls_health · EU direct · us-central1 -> europe-west4 p50 422 ms

Attestation

Nonce and digest verification for public attested gateways.

Operational
24h uptime 99.8160% Latency groups 8 Last check 2026-09-17T12:40:09.000Z
attestation_nonce · Global endpoint · europe-west4 -> us-central1 p50 1336 ms attestation_nonce · Global endpoint · us-central1 -> us-central1 p50 1227 ms attestation_nonce · EU direct · europe-west4 -> europe-west4 p50 910 ms attestation_nonce · EU direct · us-central1 -> europe-west4 p50 1457 ms attestation_nonce · US Central direct · europe-west4 -> us-central1 p50 1570 ms attestation_nonce · US Central direct · us-central1 -> us-central1 p50 889 ms attestation_nonce · US East direct · europe-west4 -> us-east4 p50 1224 ms attestation_nonce · US East direct · us-central1 -> us-east4 p50 941 ms

Billing and Settlement

Authorize, settle, and accounting path used by the gateway.

Operational
24h uptime >99.99% Latency groups 4 Last check 2026-09-17T12:40:08.000Z
gateway_authorize · Control plane · europe-west4 p50 3023 ms gateway_authorize · Control plane · us-central1 p50 913 ms gateway_settle · Control plane · europe-west4 p50 2810 ms gateway_settle · Control plane · us-central1 p50 275 ms

Provider Fallback

Fail-first route selection and rollover to the next healthy provider.

Operational
24h uptime >99.99% Latency groups 2 Last check 2026-09-17T12:40:25.000Z
provider_fallback · Control plane · europe-west4 p50 5425 ms provider_fallback · Control plane · us-central1 p50 508 ms

Image Generation

Public attested Gemini image generation and binary image validation.

Operational
24h uptime >99.99% Latency groups 0 Last check 2026-09-17T12:19:28.000Z

Model Inference

End-to-end model calls through the attested gateway: OpenAI SDK and Responses round-trips with verified output.

Operational
24h uptime >99.99% Latency groups 16 Last check 2026-09-17T12:40:25.000Z
openai_sdk_pong · Global endpoint · europe-west4 -> us-central1 p50 2256 ms openai_sdk_pong · Global endpoint · us-central1 -> us-central1 p50 1151 ms responses_pong · Global endpoint · europe-west4 -> us-central1 p50 1402 ms responses_pong · Global endpoint · us-central1 -> us-central1 p50 1186 ms openai_sdk_pong · EU direct · europe-west4 -> europe-west4 p50 4602 ms openai_sdk_pong · EU direct · us-central1 -> europe-west4 p50 5158 ms responses_pong · EU direct · europe-west4 -> europe-west4 p50 4534 ms responses_pong · EU direct · us-central1 -> europe-west4 p50 5126 ms openai_sdk_pong · US Central direct · europe-west4 -> us-central1 p50 1319 ms openai_sdk_pong · US Central direct · us-central1 -> us-central1 p50 883 ms responses_pong · US Central direct · europe-west4 -> us-central1 p50 1434 ms responses_pong · US Central direct · us-central1 -> us-central1 p50 967 ms openai_sdk_pong · US East direct · europe-west4 -> us-east4 p50 2213 ms openai_sdk_pong · US East direct · us-central1 -> us-east4 p50 2128 ms responses_pong · US East direct · europe-west4 -> us-east4 p50 2172 ms responses_pong · US East direct · us-central1 -> us-east4 p50 1871 ms

Router Core uptime

Precomputed Router Core rollups. Control Plane and upstream providers are measured separately.

WindowStatusSamplesGroups
5m up 16 10
24h down 4627 10
48h down 9552 10

Recent Events

Samples that were not operational in the last 24 hours.

Major outage
US Central Regional API

2026-09-17T02:00:00Z · attestation_nonce · europe-west4 · hourly rollup · 1 failed / 22 · attestation_http_500

Major outage
US East Regional API

2026-09-16T19:00:00Z · attestation_nonce · us-central1 · hourly rollup · 1 failed / 19 · attestation_http_500

Major outage
Canonical API

2026-09-16T16:00:00Z · attestation_nonce · us-central1 · hourly rollup · 2 failed / 19 · attestation_http_500

Major outage
EU Regional API

2026-09-16T16:00:00Z · attestation_nonce · us-central1 · hourly rollup · 1 failed / 19 · attestation_http_500

Major outage
US East Regional API

2026-09-16T14:00:00Z · attestation_nonce · europe-west4 · hourly rollup · 2 failed / 20 · attestation_http_500

View status.json View 48h rollup View monthly rollups

Every cloud runs its own probes and builds this page from its own samples, so these are independent reports rather than copies of one. If the cloud serving this page is the thing that is down, the others keep answering. Every cloud also watches every other cloud's page each pass and flags one that stops reporting.

View fleet health Google Cloud · this page AWS status Azure status
Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

By signing in you agree to the terms of service and privacy policy.