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 2026-09-16T04:18:20Z

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: 96 ms Global observed gateway p50: 168 ms Latest synthetic sample 2026-09-16T04:16:04.000Z

Router Core

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

Operational
Target 99.99% 5m uptime >99.99% 24h uptime 99.9355% 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 74 ms 10 ms 2 ms 29 ms <1 ms 1
Fresh connection Global endpoint us-central1 -> us-central1 42 ms 7 ms 2 ms 8 ms <1 ms 1
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 26 ms paid once paid once paid once <1 ms 1
Fresh connection EU direct europe-west4 -> europe-west4 71 ms 6 ms 29 ms 11 ms <1 ms 1
Fresh connection EU direct us-central1 -> europe-west4 376 ms 37 ms 106 ms 109 ms <1 ms 1
Reused connection EU direct europe-west4 -> europe-west4 13 ms paid once paid once paid once <1 ms 1
Reused connection EU direct us-central1 -> europe-west4 104 ms paid once paid once paid once <1 ms 1
Fresh connection US Central direct europe-west4 -> us-central1 398 ms 60 ms 103 ms 109 ms <1 ms 1
Fresh connection US Central direct us-central1 -> us-central1 83 ms 39 ms 2 ms 11 ms <1 ms 1
Reused connection US Central direct europe-west4 -> us-central1 103 ms paid once paid once paid once <1 ms 1
Reused connection US Central direct us-central1 -> us-central1 2 ms paid once paid once paid once <1 ms 1
Fresh connection US East direct europe-west4 -> us-east4 303 ms 7 ms 89 ms 93 ms <1 ms 1
Fresh connection US East direct us-central1 -> us-east4 166 ms 63 ms 25 ms 30 ms <1 ms 1
Reused connection US East direct europe-west4 -> us-east4 88 ms paid once paid once paid once <1 ms 1
Reused connection US East direct us-central1 -> us-east4 25 ms paid once paid once paid once <1 ms 1

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
google-ai-studio 100.00% 804 ms 0% 500
mistral 100.00% 1276 ms 0% 42
friendli 100.00% 1283 ms 0% 36
scaledown 100.00% 1303 ms 0% 3 provider_error 35
grok 100.00% 1351 ms 0% 28
cerebras 100.00% 1403 ms 0% 34
inception 100.00% 1526 ms 0% 26
telnyx 100.00% 1612 ms 0% 22
cloudflare-workers-ai 100.00% 1680 ms 0% 25
scaleway 100.00% 1683 ms 0% 32
siliconflow 100.00% 1704 ms 0% 486
atlas-cloud 100.00% 1755 ms 0% 26
azure 100.00% 1762 ms 0% 26
google-vertex 100.00% 1795 ms 0% 34
engy 100.00% 1813 ms 0% 33
reka 100.00% 1850 ms 0% 26
regolo 100.00% 1965 ms 0% 25
aion-labs 100.00% 1968 ms 0% 11 probe_config_error 4
fireworks 100.00% 1979 ms 0% 286
minimax 100.00% 2010 ms 0% 29
databricks 100.00% 2052 ms 0% 25
thinkingmachines 100.00% 2117 ms 0% 20
baseten 100.00% 2118 ms 0% 497
io-net 100.00% 2147 ms 0% 24
deepseek 100.00% 2172 ms 0% 72
alibaba 100.00% 2212 ms 0% 38
akashml 100.00% 2265 ms 0% 23
upstage 100.00% 2273 ms 0% 32
openai 100.00% 2288 ms 0% 199
wandb 100.00% 2298 ms 0% 26
venice 100.00% 2382 ms 0% 23
featherless 100.00% 2424 ms 0% 1 probe_config_error 26
pearl 100.00% 2461 ms 0% 32
nscale 100.00% 2528 ms 0% 29
together 100.00% 2667 ms 0% 118
perplexity 100.00% 2678 ms 0% 32
zero-g 100.00% 2721 ms 0% 23
stepfun 100.00% 2819 ms 0% 25
gmi 100.00% 2878 ms 0% 28
zai 100.00% 3569 ms 0% 48
confidential-ai 100.00% 3641 ms 0% 14
arcee 100.00% 4066 ms 0% 29
xiaomi 100.00% 5113 ms 0% 18
sakana 100.00% 7213 ms 0% 17 router_error 24
kimi 100.00% 7274 ms 0% 252
neurometric 100.00% 0% 500
sail-research 99.80% 2059 ms 0.2% TimeoutError 495
anthropic 99.56% 2005 ms 0.4% empty_stream 2 provider_error 225
nebius 99.40% 4185 ms 0.6% provider_error 498
deepinfra 97.76% 2117 ms 2.2% empty_stream 134
mancer 97.06% 1450 ms 2.9% TimeoutError 34
digitalocean 96.67% 1413 ms 3.3% TimeoutError 30
relace 96.43% 1940 ms 3.6% provider_error 28
nextbit 95.83% 1868 ms 4.2% provider_error 24
wafer 93.10% 1539 ms 6.9% TimeoutError 29
inceptron 88.89% 2618 ms 11.1% provider_error 27
sambanova 88.24% 3015 ms 11.8% provider_error 17
parasail 87.50% 1617 ms 12.5% provider_error 32
lightning 87.10% 2198 ms 12.9% provider_error 31
novita 86.36% 2096 ms 13.6% TimeoutError 22
makora 85.00% 1882 ms 15.0% TimeoutError 1 unsupported_route 20
tinfoil 82.44% 3379 ms 17.6% provider_error 262
chutes 77.78% 7680 ms 22.2% TimeoutError 36
morph 67.65% 1994 ms 32.4% provider_error 34
phala 56.00% 3003 ms 44.0% provider_error 25
nvidia-nim 40.62% 3056 ms 59.4% TimeoutError 32
near-ai 3.85% 3555 ms 96.2% provider_error 26
kling 0.00% 100.0% provider_error 1

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 · 6.45x burn 3 bad / 4651 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 99.8406% Latency groups 4 Last check 2026-09-16T04:15:44.000Z
attestation_nonce · Global endpoint · europe-west4 -> us-central1 p50 1383 ms attestation_nonce · Global endpoint · us-central1 -> us-central1 p50 1026 ms tls_health · Global endpoint · europe-west4 -> us-central1 p50 101 ms tls_health · Global endpoint · us-central1 -> us-central1 p50 336 ms

US Central Regional API

US Central attested TLS reachability and trust checks.

Operational
24h uptime 99.8937% Latency groups 4 Last check 2026-09-16T04:15:44.000Z
attestation_nonce · US Central direct · europe-west4 -> us-central1 p50 2146 ms attestation_nonce · US Central direct · us-central1 -> us-central1 p50 1778 ms tls_health · US Central direct · europe-west4 -> us-central1 p50 411 ms tls_health · US Central direct · us-central1 -> us-central1 p50 86 ms

US East Regional API

US East attested TLS reachability and trust checks.

Operational
24h uptime 99.8406% Latency groups 4 Last check 2026-09-16T04:15:44.000Z
attestation_nonce · US East direct · europe-west4 -> us-east4 p50 1519 ms attestation_nonce · US East direct · us-central1 -> us-east4 p50 1192 ms tls_health · US East direct · europe-west4 -> us-east4 p50 310 ms tls_health · US East direct · us-central1 -> us-east4 p50 168 ms

EU Regional API

EU attested TLS reachability and trust checks.

Operational
24h uptime 99.7343% Latency groups 4 Last check 2026-09-16T04:15:43.000Z
attestation_nonce · EU direct · europe-west4 -> europe-west4 p50 874 ms attestation_nonce · EU direct · us-central1 -> europe-west4 p50 2026 ms tls_health · EU direct · europe-west4 -> europe-west4 p50 96 ms tls_health · EU direct · us-central1 -> europe-west4 p50 386 ms

Attestation

Nonce and digest verification for public attested gateways.

Operational
24h uptime 99.6546% Latency groups 8 Last check 2026-09-16T04:15:44.000Z
attestation_nonce · Global endpoint · europe-west4 -> us-central1 p50 1383 ms attestation_nonce · Global endpoint · us-central1 -> us-central1 p50 1026 ms attestation_nonce · EU direct · europe-west4 -> europe-west4 p50 874 ms attestation_nonce · EU direct · us-central1 -> europe-west4 p50 2026 ms attestation_nonce · US Central direct · europe-west4 -> us-central1 p50 2146 ms attestation_nonce · US Central direct · us-central1 -> us-central1 p50 1778 ms attestation_nonce · US East direct · europe-west4 -> us-east4 p50 1519 ms attestation_nonce · US East direct · us-central1 -> us-east4 p50 1192 ms

Billing and Settlement

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

Operational
24h uptime >99.99% Latency groups 4 Last check 2026-09-16T04:15:48.000Z
gateway_authorize · Control plane · europe-west4 p50 2965 ms gateway_authorize · Control plane · us-central1 p50 912 ms gateway_settle · Control plane · europe-west4 p50 3120 ms gateway_settle · Control plane · us-central1 p50 267 ms

Provider Fallback

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

Operational
24h uptime >99.99% Latency groups 2 Last check 2026-09-16T04:16:04.000Z
provider_fallback · Control plane · europe-west4 p50 5866 ms provider_fallback · Control plane · us-central1 p50 506 ms

Image Generation

Public attested Gemini image generation and binary image validation.

Operational
24h uptime 80.0000% Latency groups 0 Last check 2026-09-16T00:19:25.000Z

Model Inference

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

Operational
24h uptime 99.9867% Latency groups 16 Last check 2026-09-16T04:15:58.000Z
openai_sdk_pong · Global endpoint · europe-west4 -> us-central1 p50 4805 ms openai_sdk_pong · Global endpoint · us-central1 -> us-central1 p50 952 ms responses_pong · Global endpoint · europe-west4 -> us-central1 p50 1025 ms responses_pong · Global endpoint · us-central1 -> us-central1 p50 1214 ms openai_sdk_pong · EU direct · europe-west4 -> europe-west4 p50 5950 ms openai_sdk_pong · EU direct · us-central1 -> europe-west4 p50 5355 ms responses_pong · EU direct · europe-west4 -> europe-west4 p50 4833 ms responses_pong · EU direct · us-central1 -> europe-west4 p50 4985 ms openai_sdk_pong · US Central direct · europe-west4 -> us-central1 p50 1025 ms openai_sdk_pong · US Central direct · us-central1 -> us-central1 p50 1158 ms responses_pong · US Central direct · europe-west4 -> us-central1 p50 1042 ms responses_pong · US Central direct · us-central1 -> us-central1 p50 1166 ms openai_sdk_pong · US East direct · europe-west4 -> us-east4 p50 2271 ms openai_sdk_pong · US East direct · us-central1 -> us-east4 p50 3133 ms responses_pong · US East direct · europe-west4 -> us-east4 p50 2265 ms responses_pong · US East direct · us-central1 -> us-east4 p50 3007 ms

Router Core uptime

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

WindowStatusSamplesGroups
5m up 10 10
24h down 4651 10
48h down 9505 10

Recent Events

Samples that were not operational in the last 24 hours.

Major outage
Image Generation

2026-09-16T00:00:00Z · image_generation · us-central1 · hourly rollup · 1 failed / 2 · invalid_image_payload

Major outage
Canonical API

2026-09-15T17:00:00Z · attestation_nonce · us-central1 · hourly rollup · 1 failed / 21 · attestation_http_500

Major outage
US East Regional API

2026-09-15T17:00:00Z · attestation_nonce · us-central1 · hourly rollup · 1 failed / 21 · attestation_http_500

Major outage
US East Regional API

2026-09-15T15:00:00Z · attestation_nonce · us-central1 · hourly rollup · 1 failed / 20 · attestation_http_500

Major outage
Canonical API

2026-09-15T14:00:00Z · attestation_nonce · europe-west4 · hourly rollup · 1 failed / 20 · attestation_http_500

Major outage
US East Regional API

2026-09-15T14:00:00Z · attestation_nonce · europe-west4 · hourly rollup · 1 failed / 20 · attestation_http_500

Major outage
Canonical API

2026-09-15T08:00:00Z · attestation_nonce · europe-west4 · hourly rollup · 1 failed / 20 · attestation_http_500

Major outage
US Central Regional API

2026-09-15T08:00:00Z · attestation_nonce · europe-west4 · hourly rollup · 1 failed / 20 · attestation_http_500

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.