Find a model

Browse the full catalog →
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 2026-11-11T15:38:05Z

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: 125 ms Global observed gateway p50: 125 ms Latest synthetic sample 2026-11-11T15:37:12Z

Router Core

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

Operational
Target 99.99% 5m uptime >99.99% 24h uptime 99.9168% 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 99.8336% 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 Australiaeast uaenorth -> australiaeast 713 ms 26 ms 299 ms 181 ms <1 ms 2
Reused connection Australiaeast uaenorth -> australiaeast 175 ms paid once paid once paid once <1 ms 2
Fresh connection Global endpoint uaenorth -> uaenorth 249 ms 56 ms 151 ms 13 ms <1 ms 2
Reused connection Global endpoint uaenorth -> uaenorth 3 ms paid once paid once paid once <1 ms 2
Fresh connection Uaenorth uaenorth -> uaenorth 248 ms 12 ms 141 ms 36 ms <1 ms 2
Reused connection Uaenorth uaenorth -> uaenorth 4 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
mistral 100.00% 815 ms 0% — — 56
privatemode 100.00% 890 ms 0% — — 67
inceptron 100.00% 945 ms 0% — — 55
cerebras 100.00% 1023 ms 0% — — 68
nextbit-eu 100.00% 1122 ms 0% — — 52
telnyx 100.00% 1191 ms 0% — — 61
engy 100.00% 1207 ms 0% — — 61
openai 100.00% 1208 ms 0% — 1 router_error 58
zro 100.00% 1212 ms 0% — 3 provider_auth_config 62
friendli 100.00% 1218 ms 0% — — 64
deepseek 100.00% 1247 ms 0% — — 59
anthropic 100.00% 1323 ms 0% — — 58
alibaba 100.00% 1326 ms 0% — 7 probe_config_error 66
fireworks 100.00% 1330 ms 0% — — 50
scaledown 100.00% 1421 ms 0% — — 54
morph 100.00% 1502 ms 0% — — 60
google-ai-studio 100.00% 1515 ms 0% — 8 provider_error 44
coralbricks 100.00% 1571 ms 0% — — 51
neurometric 100.00% 1634 ms 0% — — 64
abliteration 100.00% 1640 ms 0% — — 59
boundless 100.00% 1652 ms 0% — — 43
crusoe 100.00% 1654 ms 0% — — 70
confidential-ai 100.00% 1757 ms 0% — — 58
kimi 100.00% 1792 ms 0% — — 59
xiaomi 100.00% 1814 ms 0% — — 66
byteplus 100.00% 1833 ms 0% — — 57
pearl 100.00% 1841 ms 0% — — 55
databricks 100.00% 1911 ms 0% — 6 provider_auth_config 44
zai 100.00% 1940 ms 0% — 1 router_error 78
siliconflow 100.00% 2077 ms 0% — — 66
thinkingmachines 100.00% 2250 ms 0% — — 70
tinfoil 100.00% 2256 ms 0% — — 70
streamlake 100.00% 2263 ms 0% — — 71
gmi 100.00% 2833 ms 0% — — 60
azure 100.00% 2897 ms 0% — — 58
amazon-bedrock 100.00% 4527 ms 0% — — 57
grok 98.59% 1468 ms 1.4% server_error — 71
minimax 98.59% 1909 ms 1.4% TimeoutError — 71
makora 98.51% 1350 ms 1.5% api_error 9 unsupported_route 67
atlas-cloud 98.51% 1806 ms 1.5% provider_error 4 provider_error 67
wafer 98.48% 972 ms 1.5% TimeoutError — 66
baseten 98.44% 1389 ms 1.6% TimeoutError — 64
together 98.21% 1190 ms 1.8% TimeoutError — 56
nebius 98.11% 1077 ms 1.9% TimeoutError 1 unsupported_route 53
phala 98.04% 2501 ms 2.0% TimeoutError 16 unsupported_route 51
tencent 97.96% 2096 ms 2.0% TimeoutError 1 unsupported_route 49
parasail 96.92% 1134 ms 3.1% provider_error — 65
digitalocean 96.83% 1882 ms 3.2% internal_error — 63
cloudflare-workers-ai 96.72% 2448 ms 3.3% TimeoutError 3 router_error 61
novita 96.55% 1737 ms 3.5% empty_stream 2 unsupported_route 58
zero-g 96.43% 3029 ms 3.6% server_error — 56
venice 96.36% 1563 ms 3.6% TimeoutError — 55
deepinfra 94.23% 1563 ms 5.8% TimeoutError 1 probe_config_error 52
fortanix 90.62% 1818 ms 9.4% provider_error — 32
muna 75.93% 1408 ms 24.1% rate_limit_error — 54
chutes 55.32% 13038 ms 44.7% TimeoutError — 47
abliterate 0.00% — 100.0% provider_error — 62
aion-labs 0.00% — 100.0% provider_error — 64
akashml 0.00% — 100.0% provider_error — 47
arcee 0.00% — 100.0% provider_error — 66
featherless 0.00% — 100.0% provider_error — 48
google-vertex 0.00% — 100.0% provider_error — 80
greenference 0.00% — 100.0% provider_error — 57
inception 0.00% — 100.0% provider_error — 63
io-net 0.00% — 100.0% provider_error — 69
lyceum 0.00% — 100.0% provider_error — 65
mancer 0.00% — 100.0% provider_error — 56
maple 0.00% — 100.0% provider_error — 64
meta 0.00% — 100.0% provider_error — 64
near-ai 0.00% — 100.0% provider_error — 67
nextbit 0.00% — 100.0% provider_error — 52
nscale 0.00% — 100.0% provider_error — 68
nvidia-nim 0.00% — 100.0% provider_error — 86
regolo 0.00% — 100.0% provider_error — 49
reka 0.00% — 100.0% provider_error — 47
relace 0.00% — 100.0% provider_error — 61
sail-research 0.00% — 100.0% provider_error — 62
sakana 0.00% — 100.0% provider_error — 64
sambanova 0.00% — 100.0% provider_error — 57
scaleway 0.00% — 100.0% provider_error — 66
stepfun 0.00% — 100.0% provider_error — 64
upstage 0.00% — 100.0% provider_error — 51
wandb 0.00% — 100.0% provider_error — 61

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 · 8.32x burn 1 bad / 1202 samples
Watch Control Plane · 24h · 16.64x burn 1 bad / 601 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 99.9192% Latency groups 2 Last check 2026-11-11T15:37:10Z
attestation_nonce · Global endpoint · uaenorth -> uaenorth p50 135 ms tls_health · Global endpoint · uaenorth -> uaenorth p50 125 ms

UAE North Gateway (Dubai)

Azure confidential container addressed directly: publicly-trusted TLS minted inside the TEE and SEV-SNP attestation through MAA from a healthy UAE North enclave behind it.

Operational
24h uptime 99.7577% Latency groups 2 Last check 2026-11-11T15:37:10Z
attestation_nonce · Uaenorth · uaenorth -> uaenorth p50 151 ms tls_health · Uaenorth · uaenorth -> uaenorth p50 116 ms

Australia East Gateway (Sydney)

Azure confidential container addressed directly: publicly-trusted TLS minted inside the TEE and SEV-SNP attestation through MAA from a healthy Australia East enclave behind it.

Operational
24h uptime 99.9192% Latency groups 2 Last check 2026-11-11T15:37:10Z
attestation_nonce · Australiaeast · uaenorth -> australiaeast p50 716 ms tls_health · Australiaeast · uaenorth -> australiaeast p50 666 ms

Attestation

Nonce and digest verification for public attested gateways.

Operational
24h uptime 99.8384% Latency groups 1 Last check 2026-11-11T15:37:10Z
attestation_nonce · Global endpoint · uaenorth -> uaenorth p50 135 ms

Model Inference

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

Operational
24h uptime 99.9192% Latency groups 2 Last check 2026-11-11T15:37:12Z
openai_sdk_pong · Global endpoint · uaenorth -> uaenorth p50 1755 ms responses_pong · Global endpoint · uaenorth -> uaenorth p50 1681 ms

Router Core uptime

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

WindowStatusSamplesGroups
5m up 4 2
24h degraded 1202 2
48h degraded 2452 2

Monthly Router Core reliability

MonthStatusUptimeSamples
2026-11 degraded 99.9851% 13388
2026-10 degraded 99.9480% 38460
2026-09 degraded 99.9946% 37110
2026-08 trust degraded 99.5161% 45462

Recent Events

Samples that were not operational in the last 24 hours.

Major outage
UAE North Gateway (Dubai)

2026-11-11T03:00:00Z · attestation_nonce · uaenorth · hourly rollup · 1 failed / 25 · ConnectTimeout

Major outage
UAE North Gateway (Dubai)

2026-11-11T03:00:00Z · tls_health · uaenorth · hourly rollup · 1 failed / 25 · ConnectTimeout

Major outage
Model Inference

2026-11-10T20:00:00Z · openai_sdk_pong · uaenorth · hourly rollup · 1 failed / 26 · router_error

Major outage
Canonical API

2026-11-10T16:00:00Z · attestation_nonce · uaenorth · hourly rollup · 1 failed / 26 · ConnectTimeout

Major outage
UAE North Gateway (Dubai)

2026-11-10T16:00:00Z · tls_health · uaenorth · hourly rollup · 1 failed / 26 · ConnectTimeout

Major outage
Australia East Gateway (Sydney)

2026-11-10T16:00:00Z · tls_health · uaenorth · hourly rollup · 1 failed / 26 · ConnectTimeout

Major outage
Uncategorized

2026-11-10T16:00:00Z · control_plane_health · uaenorth · hourly rollup · 1 failed / 26 · ConnectTimeout

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.

New to TrustedRouter?

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